From d73940758a8fcb6e05d99fc7fcfa1978bec5ee2e Mon Sep 17 00:00:00 2001 From: Sandeep Mistry Date: Mon, 8 Apr 2019 15:05:59 -0400 Subject: [PATCH 01/50] Add URL Encoder class --- keywords.txt | 3 +++ src/ArduinoHttpClient.h | 1 + src/URLEncoder.cpp | 53 +++++++++++++++++++++++++++++++++++++++++ src/URLEncoder.h | 25 +++++++++++++++++++ 4 files changed, 82 insertions(+) create mode 100644 src/URLEncoder.cpp create mode 100644 src/URLEncoder.h diff --git a/keywords.txt b/keywords.txt index 27cd516..1b4bd2c 100644 --- a/keywords.txt +++ b/keywords.txt @@ -9,6 +9,7 @@ ArduinoHttpClient KEYWORD1 HttpClient KEYWORD1 WebSocketClient KEYWORD1 +URLEncoder KEYWORD1 ####################################### # Methods and Functions (KEYWORD2) @@ -47,6 +48,8 @@ isFinal KEYWORD2 readString KEYWORD2 ping KEYWORD2 +encode KEYWORD2 + ####################################### # Constants (LITERAL1) ####################################### diff --git a/src/ArduinoHttpClient.h b/src/ArduinoHttpClient.h index 578733f..abb8494 100644 --- a/src/ArduinoHttpClient.h +++ b/src/ArduinoHttpClient.h @@ -7,5 +7,6 @@ #include "HttpClient.h" #include "WebSocketClient.h" +#include "URLEncoder.h" #endif diff --git a/src/URLEncoder.cpp b/src/URLEncoder.cpp new file mode 100644 index 0000000..7baf5a9 --- /dev/null +++ b/src/URLEncoder.cpp @@ -0,0 +1,53 @@ +// Library to simplify HTTP fetching on Arduino +// (c) Copyright Arduino. 2019 +// Released under Apache License, version 2.0 + +#include "URLEncoder.h" + +URLEncoderClass::URLEncoderClass() +{ +} + +URLEncoderClass::~URLEncoderClass() +{ +} + +String URLEncoderClass::encode(const char* str) +{ + return encode(str, strlen(str)); +} + +String URLEncoderClass::encode(const String& str) +{ + return encode(str.c_str(), str.length()); +} + +String URLEncoderClass::encode(const char* str, int length) +{ + String encoded; + + encoded.reserve(length); + + for (int i = 0; i < length; i++) { + char c = str[i]; + + const char HEX_DIGIT_MAPPER[] = {'0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'A', 'B', 'C', 'D', 'E', 'F'}; + + if (isAlphaNumeric(c) || (c == '-') || (c == '.') || (c == '_') || (c == '~')) { + encoded += c; + } else { + char s[4]; + + s[0] = '%'; + s[1] = HEX_DIGIT_MAPPER[(c >> 4) & 0xf]; + s[2] = HEX_DIGIT_MAPPER[(c & 0x0f)]; + s[3] = 0; + + encoded += s; + } + } + + return encoded; +} + +URLEncoderClass URLEncoder; diff --git a/src/URLEncoder.h b/src/URLEncoder.h new file mode 100644 index 0000000..e1859ff --- /dev/null +++ b/src/URLEncoder.h @@ -0,0 +1,25 @@ +// Library to simplify HTTP fetching on Arduino +// (c) Copyright Arduino. 2019 +// Released under Apache License, version 2.0 + +#ifndef URL_ENCODER_H +#define URL_ENCODER_H + +#include + +class URLEncoderClass +{ +public: + URLEncoderClass(); + virtual ~URLEncoderClass(); + + String encode(const char* str); + String encode(const String& str); + +private: + String encode(const char* str, int length); +}; + +extern URLEncoderClass URLEncoder; + +#endif From 5f567031d56b8a12e81ad88ea7fdc3b59d91c184 Mon Sep 17 00:00:00 2001 From: Sandeep Mistry Date: Tue, 9 Apr 2019 10:00:39 -0400 Subject: [PATCH 02/50] Make encode method's static --- src/URLEncoder.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/src/URLEncoder.h b/src/URLEncoder.h index e1859ff..bce5f17 100644 --- a/src/URLEncoder.h +++ b/src/URLEncoder.h @@ -13,11 +13,11 @@ class URLEncoderClass URLEncoderClass(); virtual ~URLEncoderClass(); - String encode(const char* str); - String encode(const String& str); + static String encode(const char* str); + static String encode(const String& str); private: - String encode(const char* str, int length); + static String encode(const char* str, int length); }; extern URLEncoderClass URLEncoder; From 7f36561e0bced5458516066ae09636e119cae0ed Mon Sep 17 00:00:00 2001 From: Sandeep Mistry Date: Tue, 9 Apr 2019 12:48:29 -0400 Subject: [PATCH 03/50] Version 0.4.0 --- CHANGELOG.md | 4 ++++ library.properties | 2 +- 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index f828d31..ac78d18 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,3 +1,7 @@ +## ArduinoHttpClient 0.4.0 - 2019.04.09 + +* Added URLEncoder helper + ## ArduinoHttpClient 0.3.2 - 2019.02.04 * Changed Flush return value resulting in compilation error. Thanks @forGGe diff --git a/library.properties b/library.properties index adb5aec..632910e 100644 --- a/library.properties +++ b/library.properties @@ -1,5 +1,5 @@ name=ArduinoHttpClient -version=0.3.2 +version=0.4.0 author=Arduino maintainer=Arduino sentence=[EXPERIMENTAL] Easily interact with web servers from Arduino, using HTTP and WebSocket's. From 208dfec4cf79794547a897bdb1c79a55f8e269f7 Mon Sep 17 00:00:00 2001 From: Park0 Date: Sun, 28 Jun 2020 11:52:27 +0200 Subject: [PATCH 04/50] ContentLength can go over 2 byte int Converted int to long to allow for more then 65535 bytes in length --- src/HttpClient.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/src/HttpClient.h b/src/HttpClient.h index 38fd799..b9f68f8 100644 --- a/src/HttpClient.h +++ b/src/HttpClient.h @@ -272,7 +272,7 @@ class HttpClient : public Client @return Length of the body, in bytes, or kNoContentLengthHeader if no Content-Length header was returned by the server */ - int contentLength(); + long contentLength(); /** Returns if the response body is chunked @return true if response body is chunked, false otherwise @@ -372,7 +372,7 @@ class HttpClient : public Client // Stores the status code for the response, once known int iStatusCode; // Stores the value of the Content-Length header, if present - int iContentLength; + long iContentLength; // How many bytes of the response body have been read by the user int iBodyLengthConsumed; // How far through a Content-Length header prefix we are From 0fac9f0033de4e1f45a9e2d2a28d326c94354163 Mon Sep 17 00:00:00 2001 From: Park0 Date: Sun, 28 Jun 2020 11:53:31 +0200 Subject: [PATCH 05/50] ContentLength can go over 2 byte int Converted int to long to allow for more then 65535 bytes in length --- src/HttpClient.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/HttpClient.cpp b/src/HttpClient.cpp index 7517eea..33ac681 100644 --- a/src/HttpClient.cpp +++ b/src/HttpClient.cpp @@ -542,7 +542,7 @@ bool HttpClient::endOfHeadersReached() return (iState == eReadingBody || iState == eReadingChunkLength || iState == eReadingBodyChunk); }; -int HttpClient::contentLength() +long HttpClient::contentLength() { // skip the response headers, if they haven't been read already if (!endOfHeadersReached()) From 9a5afdfc741a35ec18a71295c508c1142391ec09 Mon Sep 17 00:00:00 2001 From: Vaibhav Patel Date: Fri, 26 Feb 2021 05:01:05 -0500 Subject: [PATCH 06/50] Fix -Wlogical-not-parentheses warning (#79) * Fix -Wlogical-not-parentheses warning The warning occurs because `operator!()` has higher precedence than `operator>()`. Alternatively, we can use: ``` iClient->connect(iServerAddress, iServerPort) <= 0 ``` --- src/HttpClient.cpp | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/src/HttpClient.cpp b/src/HttpClient.cpp index 7517eea..4f3410f 100644 --- a/src/HttpClient.cpp +++ b/src/HttpClient.cpp @@ -84,7 +84,7 @@ int HttpClient::startRequest(const char* aURLPath, const char* aHttpMethod, { if (iServerName) { - if (!iClient->connect(iServerName, iServerPort) > 0) + if (!(iClient->connect(iServerName, iServerPort) > 0)) { #ifdef LOGGING Serial.println("Connection failed"); @@ -94,7 +94,7 @@ int HttpClient::startRequest(const char* aURLPath, const char* aHttpMethod, } else { - if (!iClient->connect(iServerAddress, iServerPort) > 0) + if (!(iClient->connect(iServerAddress, iServerPort) > 0)) { #ifdef LOGGING Serial.println("Connection failed"); From 05b7dfe53d0c58706c38f2ead07f7a21d293e9ff Mon Sep 17 00:00:00 2001 From: per1234 Date: Sun, 11 Apr 2021 21:40:50 -0700 Subject: [PATCH 07/50] Configure Dependabot to check for outdated actions used in workflows Dependabot will periodically check the versions of all actions used in the repository's workflows. If any are found to be outdated, it will submit a pull request to update them. NOTE: Dependabot's PRs will sometimes try to pin to the patch version of the action (e.g., updating `uses: foo/bar@v1` to `uses: foo/bar@v2.3.4`). When the action author has provided a major version ref, use that instead (e.g., `uses: foo/bar@v2`). Dependabot will automatically close its PR once the workflow has been updated. More information: https://docs.github.com/en/github/administering-a-repository/keeping-your-actions-up-to-date-with-dependabot --- .github/dependabot.yml | 10 ++++++++++ 1 file changed, 10 insertions(+) create mode 100644 .github/dependabot.yml diff --git a/.github/dependabot.yml b/.github/dependabot.yml new file mode 100644 index 0000000..03600dd --- /dev/null +++ b/.github/dependabot.yml @@ -0,0 +1,10 @@ +# See: https://docs.github.com/en/github/administering-a-repository/configuration-options-for-dependency-updates#about-the-dependabotyml-file +version: 2 + +updates: + # Configure check for outdated GitHub Actions actions in workflows. + # See: https://docs.github.com/en/github/administering-a-repository/keeping-your-actions-up-to-date-with-dependabot + - package-ecosystem: github-actions + directory: / # Check the repository's workflows under /.github/workflows/ + schedule: + interval: daily From 42d8a204f0157066fe249e1535179bafa25665c2 Mon Sep 17 00:00:00 2001 From: per1234 Date: Sun, 11 Apr 2021 21:41:26 -0700 Subject: [PATCH 08/50] Add CI workflow to check for commonly misspelled words On every push, pull request, and periodically, use the codespell-project/actions-codespell action to check for commonly misspelled words. In the event of a false positive, the problematic word should be added, in all lowercase, to the ignore-words-list field of ./.codespellrc. Regardless of the case of the word in the false positive, it must be in all lowercase in the ignore list. The ignore list is comma-separated with no spaces. --- .codespellrc | 7 +++++++ .github/workflows/spell-check.yml | 22 ++++++++++++++++++++++ README.md | 2 ++ 3 files changed, 31 insertions(+) create mode 100644 .codespellrc create mode 100644 .github/workflows/spell-check.yml diff --git a/.codespellrc b/.codespellrc new file mode 100644 index 0000000..101edae --- /dev/null +++ b/.codespellrc @@ -0,0 +1,7 @@ +# See: https://github.com/codespell-project/codespell#using-a-config-file +[codespell] +# In the event of a false positive, add the problematic word, in all lowercase, to a comma-separated list here: +ignore-words-list = , +check-filenames = +check-hidden = +skip = ./.git diff --git a/.github/workflows/spell-check.yml b/.github/workflows/spell-check.yml new file mode 100644 index 0000000..01bee87 --- /dev/null +++ b/.github/workflows/spell-check.yml @@ -0,0 +1,22 @@ +name: Spell Check + +# See: https://docs.github.com/en/free-pro-team@latest/actions/reference/events-that-trigger-workflows +on: + push: + pull_request: + schedule: + # Run every Tuesday at 8 AM UTC to catch new misspelling detections resulting from dictionary updates. + - cron: "0 8 * * TUE" + workflow_dispatch: + repository_dispatch: + +jobs: + spellcheck: + runs-on: ubuntu-latest + + steps: + - name: Checkout repository + uses: actions/checkout@v2 + + - name: Spell check + uses: codespell-project/actions-codespell@master diff --git a/README.md b/README.md index 1b95559..b976c27 100644 --- a/README.md +++ b/README.md @@ -1,5 +1,7 @@ # ArduinoHttpClient +[![Spell Check status](https://github.com/arduino-libraries/ArduinoHttpClient/actions/workflows/spell-check.yml/badge.svg)](https://github.com/arduino-libraries/ArduinoHttpClient/actions/workflows/spell-check.yml) + ArduinoHttpClient is a library to make it easier to interact with web servers from Arduino. Derived from [Adrian McEwen's HttpClient library](https://github.com/amcewen/HttpClient) From e9897fc56834ed998ba6bb64e40aaa534bceef26 Mon Sep 17 00:00:00 2001 From: per1234 Date: Sun, 11 Apr 2021 21:53:59 -0700 Subject: [PATCH 09/50] Correct typos in comments and documentation --- CHANGELOG.md | 2 +- examples/BasicAuthGet/BasicAuthGet.ino | 2 +- examples/CustomHeader/CustomHeader.ino | 2 +- examples/DweetGet/DweetGet.ino | 2 +- examples/DweetPost/DweetPost.ino | 2 +- examples/HueBlink/HueBlink.ino | 12 ++++++------ examples/PostWithHeaders/PostWithHeaders.ino | 4 ++-- examples/SimpleDelete/SimpleDelete.ino | 2 +- examples/SimpleGet/SimpleGet.ino | 2 +- examples/SimpleHttpExample/SimpleHttpExample.ino | 8 +++----- examples/SimplePost/SimplePost.ino | 2 +- examples/SimplePut/SimplePut.ino | 2 +- examples/SimpleWebSocket/SimpleWebSocket.ino | 2 +- keywords.txt | 2 +- library.json | 2 +- library.properties | 2 +- src/HttpClient.cpp | 4 ++-- src/HttpClient.h | 4 ++-- 18 files changed, 28 insertions(+), 30 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index ac78d18..fc0e879 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -9,7 +9,7 @@ ## ArduinoHttpClient 0.3.1 - 2017.09.25 * Changed examples to support Arduino Create secret tabs -* Increase WebSocket secrect-key length to 24 characters +* Increase WebSocket secret-key length to 24 characters ## ArduinoHttpClient 0.3.0 - 2017.04.20 diff --git a/examples/BasicAuthGet/BasicAuthGet.ino b/examples/BasicAuthGet/BasicAuthGet.ino index ca801b7..861acc1 100644 --- a/examples/BasicAuthGet/BasicAuthGet.ino +++ b/examples/BasicAuthGet/BasicAuthGet.ino @@ -15,7 +15,7 @@ #include #include "arduino_secrets.h" ///////please enter your sensitive data in the Secret tab/arduino_secrets.h -/////// Wifi Settings /////// +/////// WiFi Settings /////// char ssid[] = SECRET_SSID; char pass[] = SECRET_PASS; diff --git a/examples/CustomHeader/CustomHeader.ino b/examples/CustomHeader/CustomHeader.ino index e2131eb..4b8abbb 100644 --- a/examples/CustomHeader/CustomHeader.ino +++ b/examples/CustomHeader/CustomHeader.ino @@ -15,7 +15,7 @@ #include "arduino_secrets.h" ///////please enter your sensitive data in the Secret tab/arduino_secrets.h -/////// Wifi Settings /////// +/////// WiFi Settings /////// char ssid[] = SECRET_SSID; char pass[] = SECRET_PASS; diff --git a/examples/DweetGet/DweetGet.ino b/examples/DweetGet/DweetGet.ino index d191285..1c26c35 100644 --- a/examples/DweetGet/DweetGet.ino +++ b/examples/DweetGet/DweetGet.ino @@ -20,7 +20,7 @@ #include "arduino_secrets.h" ///////please enter your sensitive data in the Secret tab/arduino_secrets.h -/////// Wifi Settings /////// +/////// WiFi Settings /////// char ssid[] = SECRET_SSID; char pass[] = SECRET_PASS; diff --git a/examples/DweetPost/DweetPost.ino b/examples/DweetPost/DweetPost.ino index f1da2b9..17e76f5 100644 --- a/examples/DweetPost/DweetPost.ino +++ b/examples/DweetPost/DweetPost.ino @@ -16,7 +16,7 @@ #include "arduino_secrets.h" ///////please enter your sensitive data in the Secret tab/arduino_secrets.h -/////// Wifi Settings /////// +/////// WiFi Settings /////// char ssid[] = SECRET_SSID; char pass[] = SECRET_PASS; diff --git a/examples/HueBlink/HueBlink.ino b/examples/HueBlink/HueBlink.ino index eab74fe..0583fe9 100644 --- a/examples/HueBlink/HueBlink.ino +++ b/examples/HueBlink/HueBlink.ino @@ -10,7 +10,7 @@ The body of the PUT request looks like this: {"on": true} or {"on":false} - This example shows how to concatenate Strings to assemble the + This example shows how to concatenate Strings to assemble the PUT request and the body of the request. modified 15 Feb 2016 @@ -23,16 +23,16 @@ #include "arduino_secrets.h" ///////please enter your sensitive data in the Secret tab/arduino_secrets.h -/////// Wifi Settings /////// +/////// WiFi Settings /////// char ssid[] = SECRET_SSID; char pass[] = SECRET_PASS; -int status = WL_IDLE_STATUS; // the Wifi radio's status +int status = WL_IDLE_STATUS; // the WiFi radio's status char hueHubIP[] = "192.168.0.3"; // IP address of the HUE bridge String hueUserName = "huebridgeusername"; // hue bridge username -// make a wifi instance and a HttpClient instance: +// make a WiFiClient instance and a HttpClient instance: WiFiClient wifi; HttpClient httpClient = HttpClient(wifi, hueHubIP); @@ -42,7 +42,7 @@ void setup() { Serial.begin(9600); while (!Serial); // wait for serial port to connect. - // attempt to connect to Wifi network: + // attempt to connect to WiFi network: while ( status != WL_CONNECTED) { Serial.print("Attempting to connect to WPA SSID: "); Serial.println(ssid); @@ -95,4 +95,4 @@ void sendRequest(int light, String cmd, String value) { Serial.print("Server response: "); Serial.println(response); Serial.println(); -} \ No newline at end of file +} diff --git a/examples/PostWithHeaders/PostWithHeaders.ino b/examples/PostWithHeaders/PostWithHeaders.ino index c2b1f0a..f97439f 100644 --- a/examples/PostWithHeaders/PostWithHeaders.ino +++ b/examples/PostWithHeaders/PostWithHeaders.ino @@ -1,7 +1,7 @@ /* POST with headers client for ArduinoHttpClient library Connects to server once every five seconds, sends a POST request - with custome headers and a request body + with custom headers and a request body created 14 Feb 2016 by Tom Igoe @@ -18,7 +18,7 @@ #include "arduino_secrets.h" ///////please enter your sensitive data in the Secret tab/arduino_secrets.h -/////// Wifi Settings /////// +/////// WiFi Settings /////// char ssid[] = SECRET_SSID; char pass[] = SECRET_PASS; diff --git a/examples/SimpleDelete/SimpleDelete.ino b/examples/SimpleDelete/SimpleDelete.ino index 120f8d4..336cb7a 100644 --- a/examples/SimpleDelete/SimpleDelete.ino +++ b/examples/SimpleDelete/SimpleDelete.ino @@ -15,7 +15,7 @@ #include "arduino_secrets.h" ///////please enter your sensitive data in the Secret tab/arduino_secrets.h -/////// Wifi Settings /////// +/////// WiFi Settings /////// char ssid[] = SECRET_SSID; char pass[] = SECRET_PASS; diff --git a/examples/SimpleGet/SimpleGet.ino b/examples/SimpleGet/SimpleGet.ino index 90d1f68..759b13f 100644 --- a/examples/SimpleGet/SimpleGet.ino +++ b/examples/SimpleGet/SimpleGet.ino @@ -14,7 +14,7 @@ #include "arduino_secrets.h" ///////please enter your sensitive data in the Secret tab/arduino_secrets.h -/////// Wifi Settings /////// +/////// WiFi Settings /////// char ssid[] = SECRET_SSID; char pass[] = SECRET_PASS; diff --git a/examples/SimpleHttpExample/SimpleHttpExample.ino b/examples/SimpleHttpExample/SimpleHttpExample.ino index f64b9ba..449d6af 100644 --- a/examples/SimpleHttpExample/SimpleHttpExample.ino +++ b/examples/SimpleHttpExample/SimpleHttpExample.ino @@ -2,7 +2,7 @@ // Released under Apache License, version 2.0 // // Simple example to show how to use the HttpClient library -// Get's the web page given at http:// and +// Gets the web page given at http:// and // outputs the content to the serial port #include @@ -14,7 +14,7 @@ #include "arduino_secrets.h" ///////please enter your sensitive data in the Secret tab/arduino_secrets.h -/////// Wifi Settings /////// +/////// WiFi Settings /////// char ssid[] = SECRET_SSID; char pass[] = SECRET_PASS; @@ -42,7 +42,7 @@ void setup() ; // wait for serial port to connect. Needed for native USB port only } - // attempt to connect to Wifi network: + // attempt to connect to WiFi network: Serial.print("Attempting to connect to WPA SSID: "); Serial.println(ssid); while (WiFi.begin(ssid, pass) != WL_CONNECTED) { @@ -129,5 +129,3 @@ void loop() // And just stop, now that we've tried a download while(1); } - - diff --git a/examples/SimplePost/SimplePost.ino b/examples/SimplePost/SimplePost.ino index a4704e5..8717438 100644 --- a/examples/SimplePost/SimplePost.ino +++ b/examples/SimplePost/SimplePost.ino @@ -14,7 +14,7 @@ #include "arduino_secrets.h" ///////please enter your sensitive data in the Secret tab/arduino_secrets.h -/////// Wifi Settings /////// +/////// WiFi Settings /////// char ssid[] = SECRET_SSID; char pass[] = SECRET_PASS; diff --git a/examples/SimplePut/SimplePut.ino b/examples/SimplePut/SimplePut.ino index 99af49f..06dcd15 100644 --- a/examples/SimplePut/SimplePut.ino +++ b/examples/SimplePut/SimplePut.ino @@ -14,7 +14,7 @@ #include "arduino_secrets.h" ///////please enter your sensitive data in the Secret tab/arduino_secrets.h -/////// Wifi Settings /////// +/////// WiFi Settings /////// char ssid[] = SECRET_SSID; char pass[] = SECRET_PASS; diff --git a/examples/SimpleWebSocket/SimpleWebSocket.ino b/examples/SimpleWebSocket/SimpleWebSocket.ino index b20d74b..32f74e1 100644 --- a/examples/SimpleWebSocket/SimpleWebSocket.ino +++ b/examples/SimpleWebSocket/SimpleWebSocket.ino @@ -15,7 +15,7 @@ #include "arduino_secrets.h" ///////please enter your sensitive data in the Secret tab/arduino_secrets.h -/////// Wifi Settings /////// +/////// WiFi Settings /////// char ssid[] = SECRET_SSID; char pass[] = SECRET_PASS; diff --git a/keywords.txt b/keywords.txt index 1b4bd2c..209c917 100644 --- a/keywords.txt +++ b/keywords.txt @@ -1,5 +1,5 @@ ####################################### -# Syntax Coloring Map For HttpClient +# Syntax Coloring Map For ArduinoHttpClient ####################################### ####################################### diff --git a/library.json b/library.json index 6bbda24..5376d0a 100644 --- a/library.json +++ b/library.json @@ -1,7 +1,7 @@ { "name": "ArduinoHttpClient", "keywords": "http, web, client, ethernet, wifi, GSM", - "description": "Easily interact with web servers from Arduino, using HTTP and WebSocket's.", + "description": "Easily interact with web servers from Arduino, using HTTP and WebSockets.", "repository": { "type": "git", diff --git a/library.properties b/library.properties index 632910e..2682599 100644 --- a/library.properties +++ b/library.properties @@ -2,7 +2,7 @@ name=ArduinoHttpClient version=0.4.0 author=Arduino maintainer=Arduino -sentence=[EXPERIMENTAL] Easily interact with web servers from Arduino, using HTTP and WebSocket's. +sentence=[EXPERIMENTAL] Easily interact with web servers from Arduino, using HTTP and WebSockets. paragraph=This library can be used for HTTP (GET, POST, PUT, DELETE) requests to a web server. It also supports exchanging messages with WebSocket servers. Based on Adrian McEwen's HttpClient library. category=Communication url=https://github.com/arduino-libraries/ArduinoHttpClient diff --git a/src/HttpClient.cpp b/src/HttpClient.cpp index 4f3410f..1c73464 100644 --- a/src/HttpClient.cpp +++ b/src/HttpClient.cpp @@ -587,7 +587,7 @@ String HttpClient::responseBody() } if (bodyLength > 0 && (unsigned int)bodyLength != response.length()) { - // failure, we did not read in reponse content length bytes + // failure, we did not read in response content length bytes return String((const char*)NULL); } @@ -685,7 +685,7 @@ int HttpClient::read() bool HttpClient::headerAvailable() { - // clear the currently store header line + // clear the currently stored header line iHeaderLine = ""; while (!endOfHeadersReached()) diff --git a/src/HttpClient.h b/src/HttpClient.h index 38fd799..6a7aa1d 100644 --- a/src/HttpClient.h +++ b/src/HttpClient.h @@ -228,7 +228,7 @@ class HttpClient : public Client */ String readHeaderName(); - /** Read the vallue of the current response header. + /** Read the value of the current response header. Returns empty string if a header is not available. */ String readHeaderValue(); @@ -341,7 +341,7 @@ class HttpClient : public Client // Number of milliseconds that we wait each time there isn't any data // available to be read (during status code and header processing) static const int kHttpWaitForDataDelay = 1000; - // Number of milliseconds that we'll wait in total without receiveing any + // Number of milliseconds that we'll wait in total without receiving any // data before returning HTTP_ERROR_TIMED_OUT (during status code and header // processing) static const int kHttpResponseTimeout = 30*1000; From 0d235030a6e8da348dde4f0b2abc3f22aaad9566 Mon Sep 17 00:00:00 2001 From: per1234 Date: Sun, 11 Apr 2021 21:54:28 -0700 Subject: [PATCH 10/50] Add CI workflow to do Arduino project-specific linting On every push, pull request, and periodically, run Arduino Lint to check for common problems not related to the project code. --- .github/workflows/check-arduino.yml | 28 ++++++++++++++++++++++++++++ README.md | 1 + 2 files changed, 29 insertions(+) create mode 100644 .github/workflows/check-arduino.yml diff --git a/.github/workflows/check-arduino.yml b/.github/workflows/check-arduino.yml new file mode 100644 index 0000000..0d969f6 --- /dev/null +++ b/.github/workflows/check-arduino.yml @@ -0,0 +1,28 @@ +name: Check Arduino + +# See: https://docs.github.com/en/free-pro-team@latest/actions/reference/events-that-trigger-workflows +on: + push: + pull_request: + schedule: + # Run every Tuesday at 8 AM UTC to catch breakage caused by new rules added to Arduino Lint. + - cron: "0 8 * * TUE" + workflow_dispatch: + repository_dispatch: + +jobs: + lint: + runs-on: ubuntu-latest + + steps: + - name: Checkout repository + uses: actions/checkout@v2 + + - name: Arduino Lint + uses: arduino/arduino-lint-action@v1 + with: + compliance: specification + library-manager: update + # Always use this setting for official repositories. Remove for 3rd party projects. + official: true + project-type: library diff --git a/README.md b/README.md index b976c27..4d99298 100644 --- a/README.md +++ b/README.md @@ -1,5 +1,6 @@ # ArduinoHttpClient +[![Check Arduino status](https://github.com/arduino-libraries/ArduinoHttpClient/actions/workflows/check-arduino.yml/badge.svg)](https://github.com/arduino-libraries/ArduinoHttpClient/actions/workflows/check-arduino.yml) [![Spell Check status](https://github.com/arduino-libraries/ArduinoHttpClient/actions/workflows/spell-check.yml/badge.svg)](https://github.com/arduino-libraries/ArduinoHttpClient/actions/workflows/spell-check.yml) ArduinoHttpClient is a library to make it easier to interact with web servers from Arduino. From d07192a7f72005a2339fe499a01d2e05c8b80aec Mon Sep 17 00:00:00 2001 From: per1234 Date: Sun, 11 Apr 2021 21:56:53 -0700 Subject: [PATCH 11/50] Add "smoke test" examples compilation CI workflow On every push or pull request that affects library source or example files, and periodically, compile all example sketches for the specified boards. --- .github/workflows/compile-examples.yml | 50 ++++++++++++++++++++++++++ README.md | 1 + 2 files changed, 51 insertions(+) create mode 100644 .github/workflows/compile-examples.yml diff --git a/.github/workflows/compile-examples.yml b/.github/workflows/compile-examples.yml new file mode 100644 index 0000000..b296861 --- /dev/null +++ b/.github/workflows/compile-examples.yml @@ -0,0 +1,50 @@ +name: Compile Examples + +# See: https://docs.github.com/en/free-pro-team@latest/actions/reference/events-that-trigger-workflows +on: + push: + paths: + - ".github/workflows/compile-examples.yml" + - "examples/**" + - "src/**" + pull_request: + paths: + - ".github/workflows/compile-examples.yml" + - "examples/**" + - "src/**" + schedule: + # Run every Tuesday at 8 AM UTC to catch breakage caused by changes to external resources (libraries, platforms). + - cron: "0 8 * * TUE" + workflow_dispatch: + repository_dispatch: + +jobs: + build: + name: ${{ matrix.board.fqbn }} + runs-on: ubuntu-latest + + strategy: + fail-fast: false + + matrix: + board: + - fqbn: arduino:samd:mkr1000 + platforms: | + - name: arduino:samd + + steps: + - name: Checkout repository + uses: actions/checkout@v2 + + - name: Compile examples + uses: arduino/compile-sketches@v1 + with: + github-token: ${{ secrets.GITHUB_TOKEN }} + fqbn: ${{ matrix.board.fqbn }} + platforms: ${{ matrix.board.platforms }} + libraries: | + # Install the library from the local path. + - source-path: ./ + - name: WiFi101 + sketch-paths: | + - examples diff --git a/README.md b/README.md index 4d99298..e9c163b 100644 --- a/README.md +++ b/README.md @@ -1,6 +1,7 @@ # ArduinoHttpClient [![Check Arduino status](https://github.com/arduino-libraries/ArduinoHttpClient/actions/workflows/check-arduino.yml/badge.svg)](https://github.com/arduino-libraries/ArduinoHttpClient/actions/workflows/check-arduino.yml) +[![Compile Examples status](https://github.com/arduino-libraries/ArduinoHttpClient/actions/workflows/compile-examples.yml/badge.svg)](https://github.com/arduino-libraries/ArduinoHttpClient/actions/workflows/compile-examples.yml) [![Spell Check status](https://github.com/arduino-libraries/ArduinoHttpClient/actions/workflows/spell-check.yml/badge.svg)](https://github.com/arduino-libraries/ArduinoHttpClient/actions/workflows/spell-check.yml) ArduinoHttpClient is a library to make it easier to interact with web servers from Arduino. From b9db0381749abf8c2bb3bc2656a36785d104ff3d Mon Sep 17 00:00:00 2001 From: per1234 Date: Sun, 11 Apr 2021 21:57:20 -0700 Subject: [PATCH 12/50] Report changes in memory usage that would result from merging a PR On creation or commit to a pull request, a report of the resulting change in memory usage of the examples will be commented to the PR thread. --- .github/workflows/compile-examples.yml | 12 ++++++++++++ .github/workflows/report-size-deltas.yml | 24 ++++++++++++++++++++++++ 2 files changed, 36 insertions(+) create mode 100644 .github/workflows/report-size-deltas.yml diff --git a/.github/workflows/compile-examples.yml b/.github/workflows/compile-examples.yml index b296861..d363d82 100644 --- a/.github/workflows/compile-examples.yml +++ b/.github/workflows/compile-examples.yml @@ -23,6 +23,9 @@ jobs: name: ${{ matrix.board.fqbn }} runs-on: ubuntu-latest + env: + SKETCHES_REPORTS_PATH: sketches-reports + strategy: fail-fast: false @@ -48,3 +51,12 @@ jobs: - name: WiFi101 sketch-paths: | - examples + enable-deltas-report: true + sketches-report-path: ${{ env.SKETCHES_REPORTS_PATH }} + + - name: Save sketches report as workflow artifact + uses: actions/upload-artifact@v2 + with: + if-no-files-found: error + path: ${{ env.SKETCHES_REPORTS_PATH }} + name: ${{ env.SKETCHES_REPORTS_PATH }} diff --git a/.github/workflows/report-size-deltas.yml b/.github/workflows/report-size-deltas.yml new file mode 100644 index 0000000..652be5d --- /dev/null +++ b/.github/workflows/report-size-deltas.yml @@ -0,0 +1,24 @@ +name: Report Size Deltas + +# See: https://docs.github.com/en/free-pro-team@latest/actions/reference/events-that-trigger-workflows +on: + push: + paths: + - ".github/workflows/report-size-deltas.yml" + schedule: + # Run at the minimum interval allowed by GitHub Actions. + # Note: GitHub Actions periodically has outages which result in workflow failures. + # In this event, the workflows will start passing again once the service recovers. + - cron: "*/5 * * * *" + workflow_dispatch: + repository_dispatch: + +jobs: + report: + runs-on: ubuntu-latest + steps: + - name: Comment size deltas reports to PRs + uses: arduino/report-size-deltas@v1 + with: + # The name of the workflow artifact created by the sketch compilation workflow + sketches-reports-source: sketches-reports From c014e0cdb8ff7c8550cb5a53bec14d48f84d5356 Mon Sep 17 00:00:00 2001 From: per1234 Date: Mon, 10 Jan 2022 01:00:56 -0800 Subject: [PATCH 13/50] Add GitHub Actions workflow to synchronize with shared repository labels (#120) On every push that changes relevant files, and periodically, configure the repository's issue and pull request labels according to the universal, shared, and local label configuration files. --- .github/dependabot.yml | 2 + .github/workflows/sync-labels.yml | 138 ++++++++++++++++++++++++++++++ 2 files changed, 140 insertions(+) create mode 100644 .github/workflows/sync-labels.yml diff --git a/.github/dependabot.yml b/.github/dependabot.yml index 03600dd..fa738ec 100644 --- a/.github/dependabot.yml +++ b/.github/dependabot.yml @@ -8,3 +8,5 @@ updates: directory: / # Check the repository's workflows under /.github/workflows/ schedule: interval: daily + labels: + - "topic: infrastructure" diff --git a/.github/workflows/sync-labels.yml b/.github/workflows/sync-labels.yml new file mode 100644 index 0000000..3ee6feb --- /dev/null +++ b/.github/workflows/sync-labels.yml @@ -0,0 +1,138 @@ +# Source: https://github.com/arduino/tooling-project-assets/blob/main/workflow-templates/sync-labels.md +name: Sync Labels + +# See: https://docs.github.com/en/actions/reference/events-that-trigger-workflows +on: + push: + paths: + - ".github/workflows/sync-labels.ya?ml" + - ".github/label-configuration-files/*.ya?ml" + pull_request: + paths: + - ".github/workflows/sync-labels.ya?ml" + - ".github/label-configuration-files/*.ya?ml" + schedule: + # Run daily at 8 AM UTC to sync with changes to shared label configurations. + - cron: "0 8 * * *" + workflow_dispatch: + repository_dispatch: + +env: + CONFIGURATIONS_FOLDER: .github/label-configuration-files + CONFIGURATIONS_ARTIFACT: label-configuration-files + +jobs: + check: + runs-on: ubuntu-latest + + steps: + - name: Checkout repository + uses: actions/checkout@v2 + + - name: Download JSON schema for labels configuration file + id: download-schema + uses: carlosperate/download-file-action@v1 + with: + file-url: https://raw.githubusercontent.com/arduino/tooling-project-assets/main/workflow-templates/assets/sync-labels/arduino-tooling-gh-label-configuration-schema.json + location: ${{ runner.temp }}/label-configuration-schema + + - name: Install JSON schema validator + run: | + sudo npm install \ + --global \ + ajv-cli \ + ajv-formats + + - name: Validate local labels configuration + run: | + # See: https://github.com/ajv-validator/ajv-cli#readme + ajv validate \ + --all-errors \ + -c ajv-formats \ + -s "${{ steps.download-schema.outputs.file-path }}" \ + -d "${{ env.CONFIGURATIONS_FOLDER }}/*.{yml,yaml}" + + download: + needs: check + runs-on: ubuntu-latest + + strategy: + matrix: + filename: + # Filenames of the shared configurations to apply to the repository in addition to the local configuration. + # https://github.com/arduino/tooling-project-assets/blob/main/workflow-templates/assets/sync-labels + - universal.yml + + steps: + - name: Download + uses: carlosperate/download-file-action@v1 + with: + file-url: https://raw.githubusercontent.com/arduino/tooling-project-assets/main/workflow-templates/assets/sync-labels/${{ matrix.filename }} + + - name: Pass configuration files to next job via workflow artifact + uses: actions/upload-artifact@v2 + with: + path: | + *.yaml + *.yml + if-no-files-found: error + name: ${{ env.CONFIGURATIONS_ARTIFACT }} + + sync: + needs: download + runs-on: ubuntu-latest + + steps: + - name: Set environment variables + run: | + # See: https://docs.github.com/en/actions/reference/workflow-commands-for-github-actions#setting-an-environment-variable + echo "MERGED_CONFIGURATION_PATH=${{ runner.temp }}/labels.yml" >> "$GITHUB_ENV" + + - name: Determine whether to dry run + id: dry-run + if: > + github.event_name == 'pull_request' || + ( + ( + github.event_name == 'push' || + github.event_name == 'workflow_dispatch' + ) && + github.ref != format('refs/heads/{0}', github.event.repository.default_branch) + ) + run: | + # Use of this flag in the github-label-sync command will cause it to only check the validity of the + # configuration. + echo "::set-output name=flag::--dry-run" + + - name: Checkout repository + uses: actions/checkout@v2 + + - name: Download configuration files artifact + uses: actions/download-artifact@v2 + with: + name: ${{ env.CONFIGURATIONS_ARTIFACT }} + path: ${{ env.CONFIGURATIONS_FOLDER }} + + - name: Remove unneeded artifact + uses: geekyeggo/delete-artifact@v1 + with: + name: ${{ env.CONFIGURATIONS_ARTIFACT }} + + - name: Merge label configuration files + run: | + # Merge all configuration files + shopt -s extglob + cat "${{ env.CONFIGURATIONS_FOLDER }}"/*.@(yml|yaml) > "${{ env.MERGED_CONFIGURATION_PATH }}" + + - name: Install github-label-sync + run: sudo npm install --global github-label-sync + + - name: Sync labels + env: + GITHUB_ACCESS_TOKEN: ${{ secrets.GITHUB_TOKEN }} + run: | + # See: https://github.com/Financial-Times/github-label-sync + github-label-sync \ + --labels "${{ env.MERGED_CONFIGURATION_PATH }}" \ + ${{ steps.dry-run.outputs.flag }} \ + ${{ github.repository }} From 09c53095e3e25549554fe20de6fc5147cff5bf5b Mon Sep 17 00:00:00 2001 From: Pablo Clemente Date: Tue, 25 Jan 2022 12:00:21 +0100 Subject: [PATCH 14/50] Added configurabel WebSocket tx buffer size --- src/WebSocketClient.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/src/WebSocketClient.h b/src/WebSocketClient.h index 4b009e6..96eb6d2 100644 --- a/src/WebSocketClient.h +++ b/src/WebSocketClient.h @@ -8,6 +8,10 @@ #include "HttpClient.h" +#ifndef WS_TX_BUFFER_SIZE + #define WS_TX_BUFFER_SIZE 128 +#endif + static const int TYPE_CONTINUATION = 0x0; static const int TYPE_TEXT = 0x1; static const int TYPE_BINARY = 0x2; @@ -86,7 +90,7 @@ class WebSocketClient : public HttpClient private: bool iTxStarted; uint8_t iTxMessageType; - uint8_t iTxBuffer[128]; + uint8_t iTxBuffer[WS_TX_BUFFER_SIZE]; uint64_t iTxSize; uint8_t iRxOpCode; From 527967d010b0b2e290ca051e6ce9e6c821f00c58 Mon Sep 17 00:00:00 2001 From: carbotaniuman <41451839+carbotaniuman@users.noreply.github.com> Date: Tue, 1 Mar 2022 08:07:10 -0600 Subject: [PATCH 15/50] Reduce timeout from 1000ms to 100ms Using this with the Arduino `WiFiClient` makes simple requests really slow. Reduce the timeout in order to make it faster. --- src/HttpClient.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/HttpClient.h b/src/HttpClient.h index 6a7aa1d..1aeb1d5 100644 --- a/src/HttpClient.h +++ b/src/HttpClient.h @@ -340,7 +340,7 @@ class HttpClient : public Client // Number of milliseconds that we wait each time there isn't any data // available to be read (during status code and header processing) - static const int kHttpWaitForDataDelay = 1000; + static const int kHttpWaitForDataDelay = 100; // Number of milliseconds that we'll wait in total without receiving any // data before returning HTTP_ERROR_TIMED_OUT (during status code and header // processing) From 2b74b7a619bff7ed9226a2c131d297afd842f0a4 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Wed, 2 Mar 2022 17:11:28 +0000 Subject: [PATCH 16/50] Bump actions/checkout from 2 to 3 Bumps [actions/checkout](https://github.com/actions/checkout) from 2 to 3. - [Release notes](https://github.com/actions/checkout/releases) - [Changelog](https://github.com/actions/checkout/blob/main/CHANGELOG.md) - [Commits](https://github.com/actions/checkout/compare/v2...v3) --- updated-dependencies: - dependency-name: actions/checkout dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] --- .github/workflows/check-arduino.yml | 2 +- .github/workflows/compile-examples.yml | 2 +- .github/workflows/spell-check.yml | 2 +- .github/workflows/sync-labels.yml | 4 ++-- 4 files changed, 5 insertions(+), 5 deletions(-) diff --git a/.github/workflows/check-arduino.yml b/.github/workflows/check-arduino.yml index 0d969f6..3e0d26c 100644 --- a/.github/workflows/check-arduino.yml +++ b/.github/workflows/check-arduino.yml @@ -16,7 +16,7 @@ jobs: steps: - name: Checkout repository - uses: actions/checkout@v2 + uses: actions/checkout@v3 - name: Arduino Lint uses: arduino/arduino-lint-action@v1 diff --git a/.github/workflows/compile-examples.yml b/.github/workflows/compile-examples.yml index d363d82..c5ab21f 100644 --- a/.github/workflows/compile-examples.yml +++ b/.github/workflows/compile-examples.yml @@ -37,7 +37,7 @@ jobs: steps: - name: Checkout repository - uses: actions/checkout@v2 + uses: actions/checkout@v3 - name: Compile examples uses: arduino/compile-sketches@v1 diff --git a/.github/workflows/spell-check.yml b/.github/workflows/spell-check.yml index 01bee87..3f6b03f 100644 --- a/.github/workflows/spell-check.yml +++ b/.github/workflows/spell-check.yml @@ -16,7 +16,7 @@ jobs: steps: - name: Checkout repository - uses: actions/checkout@v2 + uses: actions/checkout@v3 - name: Spell check uses: codespell-project/actions-codespell@master diff --git a/.github/workflows/sync-labels.yml b/.github/workflows/sync-labels.yml index 3ee6feb..4ea5755 100644 --- a/.github/workflows/sync-labels.yml +++ b/.github/workflows/sync-labels.yml @@ -27,7 +27,7 @@ jobs: steps: - name: Checkout repository - uses: actions/checkout@v2 + uses: actions/checkout@v3 - name: Download JSON schema for labels configuration file id: download-schema @@ -105,7 +105,7 @@ jobs: echo "::set-output name=flag::--dry-run" - name: Checkout repository - uses: actions/checkout@v2 + uses: actions/checkout@v3 - name: Download configuration files artifact uses: actions/download-artifact@v2 From 533711d23a4f5650808408a82464e6b89d855f21 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Fri, 8 Apr 2022 17:08:54 +0000 Subject: [PATCH 17/50] Bump actions/upload-artifact from 2 to 3 Bumps [actions/upload-artifact](https://github.com/actions/upload-artifact) from 2 to 3. - [Release notes](https://github.com/actions/upload-artifact/releases) - [Commits](https://github.com/actions/upload-artifact/compare/v2...v3) --- updated-dependencies: - dependency-name: actions/upload-artifact dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] --- .github/workflows/compile-examples.yml | 2 +- .github/workflows/sync-labels.yml | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/.github/workflows/compile-examples.yml b/.github/workflows/compile-examples.yml index c5ab21f..17cbc1f 100644 --- a/.github/workflows/compile-examples.yml +++ b/.github/workflows/compile-examples.yml @@ -55,7 +55,7 @@ jobs: sketches-report-path: ${{ env.SKETCHES_REPORTS_PATH }} - name: Save sketches report as workflow artifact - uses: actions/upload-artifact@v2 + uses: actions/upload-artifact@v3 with: if-no-files-found: error path: ${{ env.SKETCHES_REPORTS_PATH }} diff --git a/.github/workflows/sync-labels.yml b/.github/workflows/sync-labels.yml index 4ea5755..1d969d5 100644 --- a/.github/workflows/sync-labels.yml +++ b/.github/workflows/sync-labels.yml @@ -70,7 +70,7 @@ jobs: file-url: https://raw.githubusercontent.com/arduino/tooling-project-assets/main/workflow-templates/assets/sync-labels/${{ matrix.filename }} - name: Pass configuration files to next job via workflow artifact - uses: actions/upload-artifact@v2 + uses: actions/upload-artifact@v3 with: path: | *.yaml From 033387f9ff6c415f2b4fb55211d8e419a7c7c101 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Fri, 8 Apr 2022 17:08:57 +0000 Subject: [PATCH 18/50] Bump actions/download-artifact from 2 to 3 Bumps [actions/download-artifact](https://github.com/actions/download-artifact) from 2 to 3. - [Release notes](https://github.com/actions/download-artifact/releases) - [Commits](https://github.com/actions/download-artifact/compare/v2...v3) --- updated-dependencies: - dependency-name: actions/download-artifact dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] --- .github/workflows/sync-labels.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/sync-labels.yml b/.github/workflows/sync-labels.yml index 4ea5755..e84e803 100644 --- a/.github/workflows/sync-labels.yml +++ b/.github/workflows/sync-labels.yml @@ -108,7 +108,7 @@ jobs: uses: actions/checkout@v3 - name: Download configuration files artifact - uses: actions/download-artifact@v2 + uses: actions/download-artifact@v3 with: name: ${{ env.CONFIGURATIONS_ARTIFACT }} path: ${{ env.CONFIGURATIONS_FOLDER }} From b7fe7f78d4510119e7735a85a9e4115bc5baf8b7 Mon Sep 17 00:00:00 2001 From: per1234 Date: Sun, 24 Apr 2022 21:52:33 -0700 Subject: [PATCH 19/50] Remove superfluous and broken manifest file (#133) `library.json` is PlatformIO's native library manifest file but Arduino's `library.properties` is also supported by PlatformIO: https://docs.platformio.org/en/latest/librarymanager/creating.html#creating-library The `library.json` file was missing the required `version` field: https://docs.platformio.org/en/latest/librarymanager/config.html#version Although it could be added, experience with other libraries indicates that it is not really realistic to expect two manifest files to be properly maintained. Since the Arduino development software and the Arduino Library Manager requires `library.properties`, if we are to have only one the choice of keeping `library.properties` and removing `library.json` is clear. --- library.json | 12 ------------ 1 file changed, 12 deletions(-) delete mode 100644 library.json diff --git a/library.json b/library.json deleted file mode 100644 index 5376d0a..0000000 --- a/library.json +++ /dev/null @@ -1,12 +0,0 @@ -{ - "name": "ArduinoHttpClient", - "keywords": "http, web, client, ethernet, wifi, GSM", - "description": "Easily interact with web servers from Arduino, using HTTP and WebSockets.", - "repository": - { - "type": "git", - "url": "https://github.com/arduino-libraries/ArduinoHttpClient.git" - }, - "frameworks": "arduino", - "platforms": "*" -} From 1f50562ffc1a37be45766380bebb143db1094ab6 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Wed, 12 Oct 2022 17:10:08 +0000 Subject: [PATCH 20/50] Bump geekyeggo/delete-artifact from 1 to 2 Bumps [geekyeggo/delete-artifact](https://github.com/geekyeggo/delete-artifact) from 1 to 2. - [Release notes](https://github.com/geekyeggo/delete-artifact/releases) - [Commits](https://github.com/geekyeggo/delete-artifact/compare/v1...v2) --- updated-dependencies: - dependency-name: geekyeggo/delete-artifact dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] --- .github/workflows/sync-labels.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/sync-labels.yml b/.github/workflows/sync-labels.yml index 986bda6..10abaea 100644 --- a/.github/workflows/sync-labels.yml +++ b/.github/workflows/sync-labels.yml @@ -114,7 +114,7 @@ jobs: path: ${{ env.CONFIGURATIONS_FOLDER }} - name: Remove unneeded artifact - uses: geekyeggo/delete-artifact@v1 + uses: geekyeggo/delete-artifact@v2 with: name: ${{ env.CONFIGURATIONS_ARTIFACT }} From 8fc4883140e95be88781274d9e9c227e2030d9e9 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Mon, 24 Oct 2022 17:52:24 +0000 Subject: [PATCH 21/50] Bump carlosperate/download-file-action from 1 to 2 Bumps [carlosperate/download-file-action](https://github.com/carlosperate/download-file-action) from 1 to 2. - [Release notes](https://github.com/carlosperate/download-file-action/releases) - [Commits](https://github.com/carlosperate/download-file-action/compare/v1...v2) --- updated-dependencies: - dependency-name: carlosperate/download-file-action dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] --- .github/workflows/sync-labels.yml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/.github/workflows/sync-labels.yml b/.github/workflows/sync-labels.yml index 10abaea..94938f3 100644 --- a/.github/workflows/sync-labels.yml +++ b/.github/workflows/sync-labels.yml @@ -31,7 +31,7 @@ jobs: - name: Download JSON schema for labels configuration file id: download-schema - uses: carlosperate/download-file-action@v1 + uses: carlosperate/download-file-action@v2 with: file-url: https://raw.githubusercontent.com/arduino/tooling-project-assets/main/workflow-templates/assets/sync-labels/arduino-tooling-gh-label-configuration-schema.json location: ${{ runner.temp }}/label-configuration-schema @@ -65,7 +65,7 @@ jobs: steps: - name: Download - uses: carlosperate/download-file-action@v1 + uses: carlosperate/download-file-action@v2 with: file-url: https://raw.githubusercontent.com/arduino/tooling-project-assets/main/workflow-templates/assets/sync-labels/${{ matrix.filename }} From 8566fb4cc0098ef2c91f080f5eb877eefa0e23b6 Mon Sep 17 00:00:00 2001 From: Tim Vandecasteele Date: Sun, 9 Apr 2023 18:34:47 +0200 Subject: [PATCH 22/50] Make sure to use HttpClient when upgrading the connection for websockets Using WebSocketClient::begin I got into problems where `status = responseStatusCode();` would be trying to read the HTTP header, but because both HttpClient and WebSocketClient have a read function, the read from WebSocketClient was used, which returns a bunch of gibberish. This caused the WebSocket to think that the connection was not successfully upgraded. --- src/HttpClient.cpp | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/src/HttpClient.cpp b/src/HttpClient.cpp index 1c73464..000c763 100644 --- a/src/HttpClient.cpp +++ b/src/HttpClient.cpp @@ -421,7 +421,7 @@ int HttpClient::responseStatusCode() { if (available()) { - c = read(); + c = HttpClient::read(); if (c != -1) { switch(iState) @@ -762,7 +762,7 @@ int HttpClient::read(uint8_t *buf, size_t size) int HttpClient::readHeader() { - char c = read(); + char c = HttpClient::read(); if (endOfHeadersReached()) { From 0a1a8ab51a1ef60d5cfbea05cbc5a9020521d6d5 Mon Sep 17 00:00:00 2001 From: Alexander Entinger Date: Mon, 17 Jul 2023 09:53:42 +0200 Subject: [PATCH 23/50] Release v0.5.0. --- library.properties | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/library.properties b/library.properties index 2682599..3b7307e 100644 --- a/library.properties +++ b/library.properties @@ -1,5 +1,5 @@ name=ArduinoHttpClient -version=0.4.0 +version=0.5.0 author=Arduino maintainer=Arduino sentence=[EXPERIMENTAL] Easily interact with web servers from Arduino, using HTTP and WebSockets. From b93e3d233523f97f8a4da91016132b7ec94c52be Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Leonardo=20Jos=C3=A9?= Date: Fri, 4 Aug 2023 22:27:58 -0300 Subject: [PATCH 24/50] Add ability to set response wait time --- src/HttpClient.h | 1 + 1 file changed, 1 insertion(+) diff --git a/src/HttpClient.h b/src/HttpClient.h index 6a7aa1d..2ca2e31 100644 --- a/src/HttpClient.h +++ b/src/HttpClient.h @@ -384,6 +384,7 @@ class HttpClient : public Client // Stores the value of the current chunk length, if present int iChunkLength; uint32_t iHttpResponseTimeout; + uint32_t iHttpWaitForDataDelay; bool iConnectionClose; bool iSendDefaultRequestHeaders; String iHeaderLine; From 9b3987ca7ff6ba44a459e7401a12307711466a81 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Leonardo=20Jos=C3=A9?= Date: Fri, 4 Aug 2023 22:33:13 -0300 Subject: [PATCH 25/50] Add getter and setter functions --- src/HttpClient.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/src/HttpClient.h b/src/HttpClient.h index 2ca2e31..cf24d96 100644 --- a/src/HttpClient.h +++ b/src/HttpClient.h @@ -317,6 +317,8 @@ class HttpClient : public Client virtual operator bool() { return bool(iClient); }; virtual uint32_t httpResponseTimeout() { return iHttpResponseTimeout; }; virtual void setHttpResponseTimeout(uint32_t timeout) { iHttpResponseTimeout = timeout; }; + virtual uint32_t httpWaitForDataDelay() { return iHttpWaitForDataDelay; }; + virtual void setHttpWaitForDataDelay(uint32_t delay) { iHttpWaitForDataDelay = delay; }; protected: /** Reset internal state data back to the "just initialised" state */ From c490dde1f16875b988a45d21f9bb9678011061eb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Leonardo=20Jos=C3=A9?= Date: Fri, 4 Aug 2023 22:35:09 -0300 Subject: [PATCH 26/50] Replace delay constant by variable --- src/HttpClient.cpp | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/src/HttpClient.cpp b/src/HttpClient.cpp index 1c73464..5b07fd7 100644 --- a/src/HttpClient.cpp +++ b/src/HttpClient.cpp @@ -40,6 +40,7 @@ void HttpClient::resetState() iIsChunked = false; iChunkLength = 0; iHttpResponseTimeout = kHttpResponseTimeout; + iHttpWaitForDataDelay = kHttpWaitForDataDelay; } void HttpClient::stop() @@ -473,7 +474,7 @@ int HttpClient::responseStatusCode() { // We haven't got any data, so let's pause to allow some to // arrive - delay(kHttpWaitForDataDelay); + delay(iHttpWaitForDataDelay); } } if ( (c == '\n') && (iStatusCode < 200 && iStatusCode != 101) ) @@ -522,7 +523,7 @@ int HttpClient::skipResponseHeaders() { // We haven't got any data, so let's pause to allow some to // arrive - delay(kHttpWaitForDataDelay); + delay(iHttpWaitForDataDelay); } } if (endOfHeadersReached()) From 42e8f1023176e6c13b619f4651b6c01030120f39 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Mon, 4 Sep 2023 17:45:42 +0000 Subject: [PATCH 27/50] Bump actions/checkout from 3 to 4 Bumps [actions/checkout](https://github.com/actions/checkout) from 3 to 4. - [Release notes](https://github.com/actions/checkout/releases) - [Changelog](https://github.com/actions/checkout/blob/main/CHANGELOG.md) - [Commits](https://github.com/actions/checkout/compare/v3...v4) --- updated-dependencies: - dependency-name: actions/checkout dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] --- .github/workflows/check-arduino.yml | 2 +- .github/workflows/compile-examples.yml | 2 +- .github/workflows/spell-check.yml | 2 +- .github/workflows/sync-labels.yml | 4 ++-- 4 files changed, 5 insertions(+), 5 deletions(-) diff --git a/.github/workflows/check-arduino.yml b/.github/workflows/check-arduino.yml index 3e0d26c..adb330f 100644 --- a/.github/workflows/check-arduino.yml +++ b/.github/workflows/check-arduino.yml @@ -16,7 +16,7 @@ jobs: steps: - name: Checkout repository - uses: actions/checkout@v3 + uses: actions/checkout@v4 - name: Arduino Lint uses: arduino/arduino-lint-action@v1 diff --git a/.github/workflows/compile-examples.yml b/.github/workflows/compile-examples.yml index 17cbc1f..18ea893 100644 --- a/.github/workflows/compile-examples.yml +++ b/.github/workflows/compile-examples.yml @@ -37,7 +37,7 @@ jobs: steps: - name: Checkout repository - uses: actions/checkout@v3 + uses: actions/checkout@v4 - name: Compile examples uses: arduino/compile-sketches@v1 diff --git a/.github/workflows/spell-check.yml b/.github/workflows/spell-check.yml index 3f6b03f..ef7d894 100644 --- a/.github/workflows/spell-check.yml +++ b/.github/workflows/spell-check.yml @@ -16,7 +16,7 @@ jobs: steps: - name: Checkout repository - uses: actions/checkout@v3 + uses: actions/checkout@v4 - name: Spell check uses: codespell-project/actions-codespell@master diff --git a/.github/workflows/sync-labels.yml b/.github/workflows/sync-labels.yml index 94938f3..9cde1ac 100644 --- a/.github/workflows/sync-labels.yml +++ b/.github/workflows/sync-labels.yml @@ -27,7 +27,7 @@ jobs: steps: - name: Checkout repository - uses: actions/checkout@v3 + uses: actions/checkout@v4 - name: Download JSON schema for labels configuration file id: download-schema @@ -105,7 +105,7 @@ jobs: echo "::set-output name=flag::--dry-run" - name: Checkout repository - uses: actions/checkout@v3 + uses: actions/checkout@v4 - name: Download configuration files artifact uses: actions/download-artifact@v3 From 0a3e61acaff5eb127359e6f0cf40c8ff18203b56 Mon Sep 17 00:00:00 2001 From: Kodav <46531343+kodav@users.noreply.github.com> Date: Thu, 2 Nov 2023 16:51:50 +0700 Subject: [PATCH 28/50] Update HttpClient.cpp Add 443 port for HTTPS requests --- src/HttpClient.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/HttpClient.cpp b/src/HttpClient.cpp index 1c73464..d9fed33 100644 --- a/src/HttpClient.cpp +++ b/src/HttpClient.cpp @@ -161,7 +161,7 @@ int HttpClient::sendInitialHeaders(const char* aURLPath, const char* aHttpMethod { iClient->print("Host: "); iClient->print(iServerName); - if (iServerPort != kHttpPort) + if (iServerPort != kHttpPort && iServerPort != kHttpsPort) { iClient->print(":"); iClient->print(iServerPort); From ab3d0000f736a961cbecbd983412dbf782e84969 Mon Sep 17 00:00:00 2001 From: Kodav <46531343+kodav@users.noreply.github.com> Date: Thu, 2 Nov 2023 16:55:21 +0700 Subject: [PATCH 29/50] Update HttpClient.h --- src/HttpClient.h | 1 + 1 file changed, 1 insertion(+) diff --git a/src/HttpClient.h b/src/HttpClient.h index 6a7aa1d..1b3eb3e 100644 --- a/src/HttpClient.h +++ b/src/HttpClient.h @@ -43,6 +43,7 @@ class HttpClient : public Client public: static const int kNoContentLengthHeader =-1; static const int kHttpPort =80; + static const int kHttpsPort =443; static const char* kUserAgent; // FIXME Write longer API request, using port and user-agent, example From a721a5b6b31d6eb5bed8ffb170048f13dbb88da9 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Fri, 16 Feb 2024 08:24:56 +0100 Subject: [PATCH 30/50] Bump actions/upload-artifact from 3 to 4 (#164) Bumps [actions/upload-artifact](https://github.com/actions/upload-artifact) from 3 to 4. - [Release notes](https://github.com/actions/upload-artifact/releases) - [Commits](https://github.com/actions/upload-artifact/compare/v3...v4) --- updated-dependencies: - dependency-name: actions/upload-artifact dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> --- .github/workflows/compile-examples.yml | 2 +- .github/workflows/sync-labels.yml | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/.github/workflows/compile-examples.yml b/.github/workflows/compile-examples.yml index 18ea893..6dbcd38 100644 --- a/.github/workflows/compile-examples.yml +++ b/.github/workflows/compile-examples.yml @@ -55,7 +55,7 @@ jobs: sketches-report-path: ${{ env.SKETCHES_REPORTS_PATH }} - name: Save sketches report as workflow artifact - uses: actions/upload-artifact@v3 + uses: actions/upload-artifact@v4 with: if-no-files-found: error path: ${{ env.SKETCHES_REPORTS_PATH }} diff --git a/.github/workflows/sync-labels.yml b/.github/workflows/sync-labels.yml index 9cde1ac..7680b37 100644 --- a/.github/workflows/sync-labels.yml +++ b/.github/workflows/sync-labels.yml @@ -70,7 +70,7 @@ jobs: file-url: https://raw.githubusercontent.com/arduino/tooling-project-assets/main/workflow-templates/assets/sync-labels/${{ matrix.filename }} - name: Pass configuration files to next job via workflow artifact - uses: actions/upload-artifact@v3 + uses: actions/upload-artifact@v4 with: path: | *.yaml From 13d12a45facb356447499431d6dc23d81386ea15 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Fri, 16 Feb 2024 08:25:10 +0100 Subject: [PATCH 31/50] Bump actions/download-artifact from 3 to 4 (#165) Bumps [actions/download-artifact](https://github.com/actions/download-artifact) from 3 to 4. - [Release notes](https://github.com/actions/download-artifact/releases) - [Commits](https://github.com/actions/download-artifact/compare/v3...v4) --- updated-dependencies: - dependency-name: actions/download-artifact dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> --- .github/workflows/sync-labels.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/sync-labels.yml b/.github/workflows/sync-labels.yml index 7680b37..2e1d6e0 100644 --- a/.github/workflows/sync-labels.yml +++ b/.github/workflows/sync-labels.yml @@ -108,7 +108,7 @@ jobs: uses: actions/checkout@v4 - name: Download configuration files artifact - uses: actions/download-artifact@v3 + uses: actions/download-artifact@v4 with: name: ${{ env.CONFIGURATIONS_ARTIFACT }} path: ${{ env.CONFIGURATIONS_FOLDER }} From a6a4127294c52e00a85db7ec751f4a376525f3f4 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Fri, 16 Feb 2024 08:25:26 +0100 Subject: [PATCH 32/50] Bump geekyeggo/delete-artifact from 2 to 4 (#167) Bumps [geekyeggo/delete-artifact](https://github.com/geekyeggo/delete-artifact) from 2 to 4. - [Release notes](https://github.com/geekyeggo/delete-artifact/releases) - [Changelog](https://github.com/GeekyEggo/delete-artifact/blob/main/CHANGELOG.md) - [Commits](https://github.com/geekyeggo/delete-artifact/compare/v2...v4) --- updated-dependencies: - dependency-name: geekyeggo/delete-artifact dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> --- .github/workflows/sync-labels.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/sync-labels.yml b/.github/workflows/sync-labels.yml index 2e1d6e0..47ac50a 100644 --- a/.github/workflows/sync-labels.yml +++ b/.github/workflows/sync-labels.yml @@ -114,7 +114,7 @@ jobs: path: ${{ env.CONFIGURATIONS_FOLDER }} - name: Remove unneeded artifact - uses: geekyeggo/delete-artifact@v2 + uses: geekyeggo/delete-artifact@v4 with: name: ${{ env.CONFIGURATIONS_ARTIFACT }} From 9625575fcc63dd284842a55d6b54cba23284d6ae Mon Sep 17 00:00:00 2001 From: Alexander Entinger Date: Fri, 16 Feb 2024 08:31:45 +0100 Subject: [PATCH 33/50] Fix regression re report-size-deltas after updating actions/upload-artifact. (#171) For more information see https://github.com/arduino/report-size-deltas/blob/main/docs/FAQ.md#size-deltas-report-workflow-triggered-by-schedule-event . --- .github/workflows/compile-examples.yml | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/.github/workflows/compile-examples.yml b/.github/workflows/compile-examples.yml index 6dbcd38..0dd5ac7 100644 --- a/.github/workflows/compile-examples.yml +++ b/.github/workflows/compile-examples.yml @@ -34,6 +34,7 @@ jobs: - fqbn: arduino:samd:mkr1000 platforms: | - name: arduino:samd + artifact-name-suffix: arduino-samd-mkr1000 steps: - name: Checkout repository @@ -59,4 +60,4 @@ jobs: with: if-no-files-found: error path: ${{ env.SKETCHES_REPORTS_PATH }} - name: ${{ env.SKETCHES_REPORTS_PATH }} + name: sketches-report-${{ matrix.board.artifact-name-suffix }} From 7a6b39a1af31c175c7e999ac366f52b6a3efcba4 Mon Sep 17 00:00:00 2001 From: Alexander Entinger Date: Wed, 21 Feb 2024 06:58:53 +0100 Subject: [PATCH 34/50] Fix regression: report size delta size on PR. (#172) The necessary steps have in fact been documented here: https://github.com/arduino/report-size-deltas/blob/main/docs/FAQ.md#workflow-triggered-by-pull_request-event but I have overlooked them when I fixed the upload issue. With this PR the size deltas are - once again - reported within the PR. --- .github/workflows/compile-examples.yml | 27 ++++++++++++++++++++---- .github/workflows/report-size-deltas.yml | 24 --------------------- .gitignore | 1 + 3 files changed, 24 insertions(+), 28 deletions(-) delete mode 100644 .github/workflows/report-size-deltas.yml diff --git a/.github/workflows/compile-examples.yml b/.github/workflows/compile-examples.yml index 0dd5ac7..d7a183e 100644 --- a/.github/workflows/compile-examples.yml +++ b/.github/workflows/compile-examples.yml @@ -18,14 +18,15 @@ on: workflow_dispatch: repository_dispatch: +env: + # It's convenient to set variables for values used multiple times in the workflow. + SKETCHES_REPORTS_PATH: sketches-reports + jobs: - build: + compile: name: ${{ matrix.board.fqbn }} runs-on: ubuntu-latest - env: - SKETCHES_REPORTS_PATH: sketches-reports - strategy: fail-fast: false @@ -61,3 +62,21 @@ jobs: if-no-files-found: error path: ${{ env.SKETCHES_REPORTS_PATH }} name: sketches-report-${{ matrix.board.artifact-name-suffix }} + + # When using a matrix to compile for multiple boards, it's necessary to use a separate job for the deltas report + report: + needs: compile # Wait for the compile job to finish to get the data for the report + if: github.event_name == 'pull_request' # Only run the job when the workflow is triggered by a pull request + runs-on: ubuntu-latest + + steps: + # This step is needed to get the size data produced by the compile jobs + - name: Download sketches reports artifacts + uses: actions/download-artifact@v4 + with: + # All workflow artifacts will be downloaded to this location. + path: ${{ env.SKETCHES_REPORTS_PATH }} + + - uses: arduino/report-size-deltas@v1 + with: + sketches-reports-source: ${{ env.SKETCHES_REPORTS_PATH }} diff --git a/.github/workflows/report-size-deltas.yml b/.github/workflows/report-size-deltas.yml deleted file mode 100644 index 652be5d..0000000 --- a/.github/workflows/report-size-deltas.yml +++ /dev/null @@ -1,24 +0,0 @@ -name: Report Size Deltas - -# See: https://docs.github.com/en/free-pro-team@latest/actions/reference/events-that-trigger-workflows -on: - push: - paths: - - ".github/workflows/report-size-deltas.yml" - schedule: - # Run at the minimum interval allowed by GitHub Actions. - # Note: GitHub Actions periodically has outages which result in workflow failures. - # In this event, the workflows will start passing again once the service recovers. - - cron: "*/5 * * * *" - workflow_dispatch: - repository_dispatch: - -jobs: - report: - runs-on: ubuntu-latest - steps: - - name: Comment size deltas reports to PRs - uses: arduino/report-size-deltas@v1 - with: - # The name of the workflow artifact created by the sketch compilation workflow - sketches-reports-source: sketches-reports diff --git a/.gitignore b/.gitignore index 653acab..24a0007 100644 --- a/.gitignore +++ b/.gitignore @@ -3,3 +3,4 @@ examples/node_test_server/node_modules/ *.DS_Store */.DS_Store examples/.DS_Store +.idea/ From cf741b0dbf59ca71f49759e04e774bb670fde6b5 Mon Sep 17 00:00:00 2001 From: Andrea Gilardoni Date: Wed, 21 Feb 2024 14:41:20 +0100 Subject: [PATCH 35/50] Imported Url parser from src/http/ngx_http_parse.c from NGINX --- src/utility/LICENSE | 23 + src/utility/http_parser.c | 2470 +++++++++++++++++++++++++++++++++++++ src/utility/http_parser.h | 432 +++++++ 3 files changed, 2925 insertions(+) create mode 100644 src/utility/LICENSE create mode 100644 src/utility/http_parser.c create mode 100644 src/utility/http_parser.h diff --git a/src/utility/LICENSE b/src/utility/LICENSE new file mode 100644 index 0000000..5baf7c0 --- /dev/null +++ b/src/utility/LICENSE @@ -0,0 +1,23 @@ +http_parser.c is based on src/http/ngx_http_parse.c from NGINX copyright +Igor Sysoev. + +Additional changes are licensed under the same terms as NGINX and +copyright Joyent, Inc. and other Node contributors. All rights reserved. + +Permission is hereby granted, free of charge, to any person obtaining a copy +of this software and associated documentation files (the "Software"), to +deal in the Software without restriction, including without limitation the +rights to use, copy, modify, merge, publish, distribute, sublicense, and/or +sell copies of the Software, and to permit persons to whom the Software is +furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in +all copies or substantial portions of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING +FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS +IN THE SOFTWARE. diff --git a/src/utility/http_parser.c b/src/utility/http_parser.c new file mode 100644 index 0000000..b6bd43e --- /dev/null +++ b/src/utility/http_parser.c @@ -0,0 +1,2470 @@ +/* Based on src/http/ngx_http_parse.c from NGINX copyright Igor Sysoev + * + * Additional changes are licensed under the same terms as NGINX and + * copyright Joyent, Inc. and other Node contributors. All rights reserved. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to + * deal in the Software without restriction, including without limitation the + * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ +#include "http_parser.h" +#include +#include +#include +#include +#include +#include + +#ifndef ULLONG_MAX +# define ULLONG_MAX ((uint64_t) -1) /* 2^64-1 */ +#endif + +#ifndef MIN +# define MIN(a,b) ((a) < (b) ? (a) : (b)) +#endif + +#ifndef ARRAY_SIZE +# define ARRAY_SIZE(a) (sizeof(a) / sizeof((a)[0])) +#endif + +#ifndef BIT_AT +# define BIT_AT(a, i) \ + (!!((unsigned int) (a)[(unsigned int) (i) >> 3] & \ + (1 << ((unsigned int) (i) & 7)))) +#endif + +#ifndef ELEM_AT +# define ELEM_AT(a, i, v) ((unsigned int) (i) < ARRAY_SIZE(a) ? (a)[(i)] : (v)) +#endif + +#define SET_ERRNO(e) \ +do { \ + parser->http_errno = (e); \ +} while(0) + +#define CURRENT_STATE() p_state +#define UPDATE_STATE(V) p_state = (enum state) (V); +#define RETURN(V) \ +do { \ + parser->state = CURRENT_STATE(); \ + return (V); \ +} while (0); +#define REEXECUTE() \ + goto reexecute; \ + + +#ifdef __GNUC__ +# define LIKELY(X) __builtin_expect(!!(X), 1) +# define UNLIKELY(X) __builtin_expect(!!(X), 0) +#else +# define LIKELY(X) (X) +# define UNLIKELY(X) (X) +#endif + + +/* Run the notify callback FOR, returning ER if it fails */ +#define CALLBACK_NOTIFY_(FOR, ER) \ +do { \ + assert(HTTP_PARSER_ERRNO(parser) == HPE_OK); \ + \ + if (LIKELY(settings->on_##FOR)) { \ + parser->state = CURRENT_STATE(); \ + if (UNLIKELY(0 != settings->on_##FOR(parser))) { \ + SET_ERRNO(HPE_CB_##FOR); \ + } \ + UPDATE_STATE(parser->state); \ + \ + /* We either errored above or got paused; get out */ \ + if (UNLIKELY(HTTP_PARSER_ERRNO(parser) != HPE_OK)) { \ + return (ER); \ + } \ + } \ +} while (0) + +/* Run the notify callback FOR and consume the current byte */ +#define CALLBACK_NOTIFY(FOR) CALLBACK_NOTIFY_(FOR, p - data + 1) + +/* Run the notify callback FOR and don't consume the current byte */ +#define CALLBACK_NOTIFY_NOADVANCE(FOR) CALLBACK_NOTIFY_(FOR, p - data) + +/* Run data callback FOR with LEN bytes, returning ER if it fails */ +#define CALLBACK_DATA_(FOR, LEN, ER) \ +do { \ + assert(HTTP_PARSER_ERRNO(parser) == HPE_OK); \ + \ + if (FOR##_mark) { \ + if (LIKELY(settings->on_##FOR)) { \ + parser->state = CURRENT_STATE(); \ + if (UNLIKELY(0 != \ + settings->on_##FOR(parser, FOR##_mark, (LEN)))) { \ + SET_ERRNO(HPE_CB_##FOR); \ + } \ + UPDATE_STATE(parser->state); \ + \ + /* We either errored above or got paused; get out */ \ + if (UNLIKELY(HTTP_PARSER_ERRNO(parser) != HPE_OK)) { \ + return (ER); \ + } \ + } \ + FOR##_mark = NULL; \ + } \ +} while (0) + +/* Run the data callback FOR and consume the current byte */ +#define CALLBACK_DATA(FOR) \ + CALLBACK_DATA_(FOR, p - FOR##_mark, p - data + 1) + +/* Run the data callback FOR and don't consume the current byte */ +#define CALLBACK_DATA_NOADVANCE(FOR) \ + CALLBACK_DATA_(FOR, p - FOR##_mark, p - data) + +/* Set the mark FOR; non-destructive if mark is already set */ +#define MARK(FOR) \ +do { \ + if (!FOR##_mark) { \ + FOR##_mark = p; \ + } \ +} while (0) + +/* Don't allow the total size of the HTTP headers (including the status + * line) to exceed HTTP_MAX_HEADER_SIZE. This check is here to protect + * embedders against denial-of-service attacks where the attacker feeds + * us a never-ending header that the embedder keeps buffering. + * + * This check is arguably the responsibility of embedders but we're doing + * it on the embedder's behalf because most won't bother and this way we + * make the web a little safer. HTTP_MAX_HEADER_SIZE is still far bigger + * than any reasonable request or response so this should never affect + * day-to-day operation. + */ +#define COUNT_HEADER_SIZE(V) \ +do { \ + parser->nread += (V); \ + if (UNLIKELY(parser->nread > (HTTP_MAX_HEADER_SIZE))) { \ + SET_ERRNO(HPE_HEADER_OVERFLOW); \ + goto error; \ + } \ +} while (0) + + +#define PROXY_CONNECTION "proxy-connection" +#define CONNECTION "connection" +#define CONTENT_LENGTH "content-length" +#define TRANSFER_ENCODING "transfer-encoding" +#define UPGRADE "upgrade" +#define CHUNKED "chunked" +#define KEEP_ALIVE "keep-alive" +#define CLOSE "close" + + +static const char *method_strings[] = + { +#define XX(num, name, string) #string, + HTTP_METHOD_MAP(XX) +#undef XX + }; + + +/* Tokens as defined by rfc 2616. Also lowercases them. + * token = 1* + * separators = "(" | ")" | "<" | ">" | "@" + * | "," | ";" | ":" | "\" | <"> + * | "/" | "[" | "]" | "?" | "=" + * | "{" | "}" | SP | HT + */ +static const char tokens[256] = { +/* 0 nul 1 soh 2 stx 3 etx 4 eot 5 enq 6 ack 7 bel */ + 0, 0, 0, 0, 0, 0, 0, 0, +/* 8 bs 9 ht 10 nl 11 vt 12 np 13 cr 14 so 15 si */ + 0, 0, 0, 0, 0, 0, 0, 0, +/* 16 dle 17 dc1 18 dc2 19 dc3 20 dc4 21 nak 22 syn 23 etb */ + 0, 0, 0, 0, 0, 0, 0, 0, +/* 24 can 25 em 26 sub 27 esc 28 fs 29 gs 30 rs 31 us */ + 0, 0, 0, 0, 0, 0, 0, 0, +/* 32 sp 33 ! 34 " 35 # 36 $ 37 % 38 & 39 ' */ + 0, '!', 0, '#', '$', '%', '&', '\'', +/* 40 ( 41 ) 42 * 43 + 44 , 45 - 46 . 47 / */ + 0, 0, '*', '+', 0, '-', '.', 0, +/* 48 0 49 1 50 2 51 3 52 4 53 5 54 6 55 7 */ + '0', '1', '2', '3', '4', '5', '6', '7', +/* 56 8 57 9 58 : 59 ; 60 < 61 = 62 > 63 ? */ + '8', '9', 0, 0, 0, 0, 0, 0, +/* 64 @ 65 A 66 B 67 C 68 D 69 E 70 F 71 G */ + 0, 'a', 'b', 'c', 'd', 'e', 'f', 'g', +/* 72 H 73 I 74 J 75 K 76 L 77 M 78 N 79 O */ + 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', +/* 80 P 81 Q 82 R 83 S 84 T 85 U 86 V 87 W */ + 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', +/* 88 X 89 Y 90 Z 91 [ 92 \ 93 ] 94 ^ 95 _ */ + 'x', 'y', 'z', 0, 0, 0, '^', '_', +/* 96 ` 97 a 98 b 99 c 100 d 101 e 102 f 103 g */ + '`', 'a', 'b', 'c', 'd', 'e', 'f', 'g', +/* 104 h 105 i 106 j 107 k 108 l 109 m 110 n 111 o */ + 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', +/* 112 p 113 q 114 r 115 s 116 t 117 u 118 v 119 w */ + 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', +/* 120 x 121 y 122 z 123 { 124 | 125 } 126 ~ 127 del */ + 'x', 'y', 'z', 0, '|', 0, '~', 0 }; + + +static const int8_t unhex[256] = + {-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1 + ,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1 + ,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1 + , 0, 1, 2, 3, 4, 5, 6, 7, 8, 9,-1,-1,-1,-1,-1,-1 + ,-1,10,11,12,13,14,15,-1,-1,-1,-1,-1,-1,-1,-1,-1 + ,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1 + ,-1,10,11,12,13,14,15,-1,-1,-1,-1,-1,-1,-1,-1,-1 + ,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1 + }; + + +#if HTTP_PARSER_STRICT +# define T(v) 0 +#else +# define T(v) v +#endif + + +static const uint8_t normal_url_char[32] = { +/* 0 nul 1 soh 2 stx 3 etx 4 eot 5 enq 6 ack 7 bel */ + 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0, +/* 8 bs 9 ht 10 nl 11 vt 12 np 13 cr 14 so 15 si */ + 0 | T(2) | 0 | 0 | T(16) | 0 | 0 | 0, +/* 16 dle 17 dc1 18 dc2 19 dc3 20 dc4 21 nak 22 syn 23 etb */ + 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0, +/* 24 can 25 em 26 sub 27 esc 28 fs 29 gs 30 rs 31 us */ + 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0, +/* 32 sp 33 ! 34 " 35 # 36 $ 37 % 38 & 39 ' */ + 0 | 2 | 4 | 0 | 16 | 32 | 64 | 128, +/* 40 ( 41 ) 42 * 43 + 44 , 45 - 46 . 47 / */ + 1 | 2 | 4 | 8 | 16 | 32 | 64 | 128, +/* 48 0 49 1 50 2 51 3 52 4 53 5 54 6 55 7 */ + 1 | 2 | 4 | 8 | 16 | 32 | 64 | 128, +/* 56 8 57 9 58 : 59 ; 60 < 61 = 62 > 63 ? */ + 1 | 2 | 4 | 8 | 16 | 32 | 64 | 0, +/* 64 @ 65 A 66 B 67 C 68 D 69 E 70 F 71 G */ + 1 | 2 | 4 | 8 | 16 | 32 | 64 | 128, +/* 72 H 73 I 74 J 75 K 76 L 77 M 78 N 79 O */ + 1 | 2 | 4 | 8 | 16 | 32 | 64 | 128, +/* 80 P 81 Q 82 R 83 S 84 T 85 U 86 V 87 W */ + 1 | 2 | 4 | 8 | 16 | 32 | 64 | 128, +/* 88 X 89 Y 90 Z 91 [ 92 \ 93 ] 94 ^ 95 _ */ + 1 | 2 | 4 | 8 | 16 | 32 | 64 | 128, +/* 96 ` 97 a 98 b 99 c 100 d 101 e 102 f 103 g */ + 1 | 2 | 4 | 8 | 16 | 32 | 64 | 128, +/* 104 h 105 i 106 j 107 k 108 l 109 m 110 n 111 o */ + 1 | 2 | 4 | 8 | 16 | 32 | 64 | 128, +/* 112 p 113 q 114 r 115 s 116 t 117 u 118 v 119 w */ + 1 | 2 | 4 | 8 | 16 | 32 | 64 | 128, +/* 120 x 121 y 122 z 123 { 124 | 125 } 126 ~ 127 del */ + 1 | 2 | 4 | 8 | 16 | 32 | 64 | 0, }; + +#undef T + +enum state + { s_dead = 1 /* important that this is > 0 */ + + , s_start_req_or_res + , s_res_or_resp_H + , s_start_res + , s_res_H + , s_res_HT + , s_res_HTT + , s_res_HTTP + , s_res_first_http_major + , s_res_http_major + , s_res_first_http_minor + , s_res_http_minor + , s_res_first_status_code + , s_res_status_code + , s_res_status_start + , s_res_status + , s_res_line_almost_done + + , s_start_req + + , s_req_method + , s_req_spaces_before_url + , s_req_schema + , s_req_schema_slash + , s_req_schema_slash_slash + , s_req_server_start + , s_req_server + , s_req_server_with_at + , s_req_path + , s_req_query_string_start + , s_req_query_string + , s_req_fragment_start + , s_req_fragment + , s_req_http_start + , s_req_http_H + , s_req_http_HT + , s_req_http_HTT + , s_req_http_HTTP + , s_req_first_http_major + , s_req_http_major + , s_req_first_http_minor + , s_req_http_minor + , s_req_line_almost_done + + , s_header_field_start + , s_header_field + , s_header_value_discard_ws + , s_header_value_discard_ws_almost_done + , s_header_value_discard_lws + , s_header_value_start + , s_header_value + , s_header_value_lws + + , s_header_almost_done + + , s_chunk_size_start + , s_chunk_size + , s_chunk_parameters + , s_chunk_size_almost_done + + , s_headers_almost_done + , s_headers_done + + /* Important: 's_headers_done' must be the last 'header' state. All + * states beyond this must be 'body' states. It is used for overflow + * checking. See the PARSING_HEADER() macro. + */ + + , s_chunk_data + , s_chunk_data_almost_done + , s_chunk_data_done + + , s_body_identity + , s_body_identity_eof + + , s_message_done + }; + + +#define PARSING_HEADER(state) (state <= s_headers_done) + + +enum header_states + { h_general = 0 + , h_C + , h_CO + , h_CON + + , h_matching_connection + , h_matching_proxy_connection + , h_matching_content_length + , h_matching_transfer_encoding + , h_matching_upgrade + + , h_connection + , h_content_length + , h_transfer_encoding + , h_upgrade + + , h_matching_transfer_encoding_chunked + , h_matching_connection_token_start + , h_matching_connection_keep_alive + , h_matching_connection_close + , h_matching_connection_upgrade + , h_matching_connection_token + + , h_transfer_encoding_chunked + , h_connection_keep_alive + , h_connection_close + , h_connection_upgrade + }; + +enum http_host_state + { + s_http_host_dead = 1 + , s_http_userinfo_start + , s_http_userinfo + , s_http_host_start + , s_http_host_v6_start + , s_http_host + , s_http_host_v6 + , s_http_host_v6_end + , s_http_host_v6_zone_start + , s_http_host_v6_zone + , s_http_host_port_start + , s_http_host_port +}; + +/* Macros for character classes; depends on strict-mode */ +#define CR '\r' +#define LF '\n' +#define LOWER(c) (unsigned char)(c | 0x20) +#define IS_ALPHA(c) (LOWER(c) >= 'a' && LOWER(c) <= 'z') +#define IS_NUM(c) ((c) >= '0' && (c) <= '9') +#define IS_ALPHANUM(c) (IS_ALPHA(c) || IS_NUM(c)) +#define IS_HEX(c) (IS_NUM(c) || (LOWER(c) >= 'a' && LOWER(c) <= 'f')) +#define IS_MARK(c) ((c) == '-' || (c) == '_' || (c) == '.' || \ + (c) == '!' || (c) == '~' || (c) == '*' || (c) == '\'' || (c) == '(' || \ + (c) == ')') +#define IS_USERINFO_CHAR(c) (IS_ALPHANUM(c) || IS_MARK(c) || (c) == '%' || \ + (c) == ';' || (c) == ':' || (c) == '&' || (c) == '=' || (c) == '+' || \ + (c) == '$' || (c) == ',') + +#define STRICT_TOKEN(c) (tokens[(unsigned char)c]) + +#if HTTP_PARSER_STRICT +#define TOKEN(c) (tokens[(unsigned char)c]) +#define IS_URL_CHAR(c) (BIT_AT(normal_url_char, (unsigned char)c)) +#define IS_HOST_CHAR(c) (IS_ALPHANUM(c) || (c) == '.' || (c) == '-') +#else +#define TOKEN(c) ((c == ' ') ? ' ' : tokens[(unsigned char)c]) +#define IS_URL_CHAR(c) \ + (BIT_AT(normal_url_char, (unsigned char)c) || ((c) & 0x80)) +#define IS_HOST_CHAR(c) \ + (IS_ALPHANUM(c) || (c) == '.' || (c) == '-' || (c) == '_') +#endif + +/** + * Verify that a char is a valid visible (printable) US-ASCII + * character or %x80-FF + **/ +#define IS_HEADER_CHAR(ch) \ + (ch == CR || ch == LF || ch == 9 || ((unsigned char)ch > 31 && ch != 127)) + +#define start_state (parser->type == HTTP_REQUEST ? s_start_req : s_start_res) + + +#if HTTP_PARSER_STRICT +# define STRICT_CHECK(cond) \ +do { \ + if (cond) { \ + SET_ERRNO(HPE_STRICT); \ + goto error; \ + } \ +} while (0) +# define NEW_MESSAGE() (http_should_keep_alive(parser) ? start_state : s_dead) +#else +# define STRICT_CHECK(cond) +# define NEW_MESSAGE() start_state +#endif + + +/* Map errno values to strings for human-readable output */ +#define HTTP_STRERROR_GEN(n, s) { "HPE_" #n, s }, +static struct { + const char *name; + const char *description; +} http_strerror_tab[] = { + HTTP_ERRNO_MAP(HTTP_STRERROR_GEN) +}; +#undef HTTP_STRERROR_GEN + +int http_message_needs_eof(const http_parser *parser); + +/* Our URL parser. + * + * This is designed to be shared by http_parser_execute() for URL validation, + * hence it has a state transition + byte-for-byte interface. In addition, it + * is meant to be embedded in http_parser_parse_url(), which does the dirty + * work of turning state transitions URL components for its API. + * + * This function should only be invoked with non-space characters. It is + * assumed that the caller cares about (and can detect) the transition between + * URL and non-URL states by looking for these. + */ +static enum state +parse_url_char(enum state s, const char ch) +{ + if (ch == ' ' || ch == '\r' || ch == '\n') { + return s_dead; + } + +#if HTTP_PARSER_STRICT + if (ch == '\t' || ch == '\f') { + return s_dead; + } +#endif + + switch (s) { + case s_req_spaces_before_url: + /* Proxied requests are followed by scheme of an absolute URI (alpha). + * All methods except CONNECT are followed by '/' or '*'. + */ + + if (ch == '/' || ch == '*') { + return s_req_path; + } + + if (IS_ALPHA(ch)) { + return s_req_schema; + } + + break; + + case s_req_schema: + if (IS_ALPHA(ch)) { + return s; + } + + if (ch == ':') { + return s_req_schema_slash; + } + + break; + + case s_req_schema_slash: + if (ch == '/') { + return s_req_schema_slash_slash; + } + + break; + + case s_req_schema_slash_slash: + if (ch == '/') { + return s_req_server_start; + } + + break; + + case s_req_server_with_at: + if (ch == '@') { + return s_dead; + } + + /* FALLTHROUGH */ + case s_req_server_start: + case s_req_server: + if (ch == '/') { + return s_req_path; + } + + if (ch == '?') { + return s_req_query_string_start; + } + + if (ch == '@') { + return s_req_server_with_at; + } + + if (IS_USERINFO_CHAR(ch) || ch == '[' || ch == ']') { + return s_req_server; + } + + break; + + case s_req_path: + if (IS_URL_CHAR(ch)) { + return s; + } + + switch (ch) { + case '?': + return s_req_query_string_start; + + case '#': + return s_req_fragment_start; + } + + break; + + case s_req_query_string_start: + case s_req_query_string: + if (IS_URL_CHAR(ch)) { + return s_req_query_string; + } + + switch (ch) { + case '?': + /* allow extra '?' in query string */ + return s_req_query_string; + + case '#': + return s_req_fragment_start; + } + + break; + + case s_req_fragment_start: + if (IS_URL_CHAR(ch)) { + return s_req_fragment; + } + + switch (ch) { + case '?': + return s_req_fragment; + + case '#': + return s; + } + + break; + + case s_req_fragment: + if (IS_URL_CHAR(ch)) { + return s; + } + + switch (ch) { + case '?': + case '#': + return s; + } + + break; + + default: + break; + } + + /* We should never fall out of the switch above unless there's an error */ + return s_dead; +} + +uint32_t http_parser_execute (http_parser *parser, + const http_parser_settings *settings, + const char *data, + uint32_t len) +{ + char c, ch; + int8_t unhex_val; + const char *p = data; + const char *header_field_mark = 0; + const char *header_value_mark = 0; + const char *url_mark = 0; + const char *body_mark = 0; + const char *status_mark = 0; + enum state p_state = (enum state) parser->state; + const unsigned int lenient = parser->lenient_http_headers; + + /* We're in an error state. Don't bother doing anything. */ + if (HTTP_PARSER_ERRNO(parser) != HPE_OK) { + return 0; + } + + if (len == 0) { + switch (CURRENT_STATE()) { + case s_body_identity_eof: + /* Use of CALLBACK_NOTIFY() here would erroneously return 1 byte read if + * we got paused. + */ + CALLBACK_NOTIFY_NOADVANCE(message_complete); + return 0; + + case s_dead: + case s_start_req_or_res: + case s_start_res: + case s_start_req: + return 0; + + default: + SET_ERRNO(HPE_INVALID_EOF_STATE); + return 1; + } + } + + + if (CURRENT_STATE() == s_header_field) + header_field_mark = data; + if (CURRENT_STATE() == s_header_value) + header_value_mark = data; + switch (CURRENT_STATE()) { + case s_req_path: + case s_req_schema: + case s_req_schema_slash: + case s_req_schema_slash_slash: + case s_req_server_start: + case s_req_server: + case s_req_server_with_at: + case s_req_query_string_start: + case s_req_query_string: + case s_req_fragment_start: + case s_req_fragment: + url_mark = data; + break; + case s_res_status: + status_mark = data; + break; + default: + break; + } + + for (p=data; p != data + len; p++) { + ch = *p; + + if (PARSING_HEADER(CURRENT_STATE())) + COUNT_HEADER_SIZE(1); + +reexecute: + switch (CURRENT_STATE()) { + + case s_dead: + /* this state is used after a 'Connection: close' message + * the parser will error out if it reads another message + */ + if (LIKELY(ch == CR || ch == LF)) + break; + + SET_ERRNO(HPE_CLOSED_CONNECTION); + goto error; + + case s_start_req_or_res: + { + if (ch == CR || ch == LF) + break; + parser->flags = 0; + parser->content_length = ULLONG_MAX; + + if (ch == 'H') { + UPDATE_STATE(s_res_or_resp_H); + + CALLBACK_NOTIFY(message_begin); + } else { + parser->type = HTTP_REQUEST; + UPDATE_STATE(s_start_req); + REEXECUTE(); + } + + break; + } + + case s_res_or_resp_H: + if (ch == 'T') { + parser->type = HTTP_RESPONSE; + UPDATE_STATE(s_res_HT); + } else { + if (UNLIKELY(ch != 'E')) { + SET_ERRNO(HPE_INVALID_CONSTANT); + goto error; + } + + parser->type = HTTP_REQUEST; + parser->method = HTTP_HEAD; + parser->index = 2; + UPDATE_STATE(s_req_method); + } + break; + + case s_start_res: + { + parser->flags = 0; + parser->content_length = ULLONG_MAX; + + switch (ch) { + case 'H': + UPDATE_STATE(s_res_H); + break; + + case CR: + case LF: + break; + + default: + SET_ERRNO(HPE_INVALID_CONSTANT); + goto error; + } + + CALLBACK_NOTIFY(message_begin); + break; + } + + case s_res_H: + STRICT_CHECK(ch != 'T'); + UPDATE_STATE(s_res_HT); + break; + + case s_res_HT: + STRICT_CHECK(ch != 'T'); + UPDATE_STATE(s_res_HTT); + break; + + case s_res_HTT: + STRICT_CHECK(ch != 'P'); + UPDATE_STATE(s_res_HTTP); + break; + + case s_res_HTTP: + STRICT_CHECK(ch != '/'); + UPDATE_STATE(s_res_first_http_major); + break; + + case s_res_first_http_major: + if (UNLIKELY(ch < '0' || ch > '9')) { + SET_ERRNO(HPE_INVALID_VERSION); + goto error; + } + + parser->http_major = ch - '0'; + UPDATE_STATE(s_res_http_major); + break; + + /* major HTTP version or dot */ + case s_res_http_major: + { + if (ch == '.') { + UPDATE_STATE(s_res_first_http_minor); + break; + } + + if (!IS_NUM(ch)) { + SET_ERRNO(HPE_INVALID_VERSION); + goto error; + } + + parser->http_major *= 10; + parser->http_major += ch - '0'; + + if (UNLIKELY(parser->http_major > 999)) { + SET_ERRNO(HPE_INVALID_VERSION); + goto error; + } + + break; + } + + /* first digit of minor HTTP version */ + case s_res_first_http_minor: + if (UNLIKELY(!IS_NUM(ch))) { + SET_ERRNO(HPE_INVALID_VERSION); + goto error; + } + + parser->http_minor = ch - '0'; + UPDATE_STATE(s_res_http_minor); + break; + + /* minor HTTP version or end of request line */ + case s_res_http_minor: + { + if (ch == ' ') { + UPDATE_STATE(s_res_first_status_code); + break; + } + + if (UNLIKELY(!IS_NUM(ch))) { + SET_ERRNO(HPE_INVALID_VERSION); + goto error; + } + + parser->http_minor *= 10; + parser->http_minor += ch - '0'; + + if (UNLIKELY(parser->http_minor > 999)) { + SET_ERRNO(HPE_INVALID_VERSION); + goto error; + } + + break; + } + + case s_res_first_status_code: + { + if (!IS_NUM(ch)) { + if (ch == ' ') { + break; + } + + SET_ERRNO(HPE_INVALID_STATUS); + goto error; + } + parser->status_code = ch - '0'; + UPDATE_STATE(s_res_status_code); + break; + } + + case s_res_status_code: + { + if (!IS_NUM(ch)) { + switch (ch) { + case ' ': + UPDATE_STATE(s_res_status_start); + break; + case CR: + UPDATE_STATE(s_res_line_almost_done); + break; + case LF: + UPDATE_STATE(s_header_field_start); + break; + default: + SET_ERRNO(HPE_INVALID_STATUS); + goto error; + } + break; + } + + parser->status_code *= 10; + parser->status_code += ch - '0'; + + if (UNLIKELY(parser->status_code > 999)) { + SET_ERRNO(HPE_INVALID_STATUS); + goto error; + } + + break; + } + + case s_res_status_start: + { + if (ch == CR) { + UPDATE_STATE(s_res_line_almost_done); + break; + } + + if (ch == LF) { + UPDATE_STATE(s_header_field_start); + break; + } + + MARK(status); + UPDATE_STATE(s_res_status); + parser->index = 0; + break; + } + + case s_res_status: + if (ch == CR) { + UPDATE_STATE(s_res_line_almost_done); + CALLBACK_DATA(status); + break; + } + + if (ch == LF) { + UPDATE_STATE(s_header_field_start); + CALLBACK_DATA(status); + break; + } + + break; + + case s_res_line_almost_done: + STRICT_CHECK(ch != LF); + UPDATE_STATE(s_header_field_start); + break; + + case s_start_req: + { + if (ch == CR || ch == LF) + break; + parser->flags = 0; + parser->content_length = ULLONG_MAX; + + if (UNLIKELY(!IS_ALPHA(ch))) { + SET_ERRNO(HPE_INVALID_METHOD); + goto error; + } + + parser->method = (enum http_method) 0; + parser->index = 1; + switch (ch) { + case 'A': parser->method = HTTP_ACL; break; + case 'B': parser->method = HTTP_BIND; break; + case 'C': parser->method = HTTP_CONNECT; /* or COPY, CHECKOUT */ break; + case 'D': parser->method = HTTP_DELETE; break; + case 'G': parser->method = HTTP_GET; break; + case 'H': parser->method = HTTP_HEAD; break; + case 'L': parser->method = HTTP_LOCK; /* or LINK */ break; + case 'M': parser->method = HTTP_MKCOL; /* or MOVE, MKACTIVITY, MERGE, M-SEARCH, MKCALENDAR */ break; + case 'N': parser->method = HTTP_NOTIFY; break; + case 'O': parser->method = HTTP_OPTIONS; break; + case 'P': parser->method = HTTP_POST; + /* or PROPFIND|PROPPATCH|PUT|PATCH|PURGE */ + break; + case 'R': parser->method = HTTP_REPORT; /* or REBIND */ break; + case 'S': parser->method = HTTP_SUBSCRIBE; /* or SEARCH */ break; + case 'T': parser->method = HTTP_TRACE; break; + case 'U': parser->method = HTTP_UNLOCK; /* or UNSUBSCRIBE, UNBIND, UNLINK */ break; + default: + SET_ERRNO(HPE_INVALID_METHOD); + goto error; + } + UPDATE_STATE(s_req_method); + + CALLBACK_NOTIFY(message_begin); + + break; + } + + case s_req_method: + { + const char *matcher; + if (UNLIKELY(ch == '\0')) { + SET_ERRNO(HPE_INVALID_METHOD); + goto error; + } + + matcher = method_strings[parser->method]; + if (ch == ' ' && matcher[parser->index] == '\0') { + UPDATE_STATE(s_req_spaces_before_url); + } else if (ch == matcher[parser->index]) { + ; /* nada */ + } else if (IS_ALPHA(ch)) { + + switch (parser->method << 16 | parser->index << 8 | ch) { +#define XX(meth, pos, ch, new_meth) \ + case (HTTP_##meth << 16 | pos << 8 | ch): \ + parser->method = HTTP_##new_meth; break; + + XX(POST, 1, 'U', PUT) + XX(POST, 1, 'A', PATCH) + XX(CONNECT, 1, 'H', CHECKOUT) + XX(CONNECT, 2, 'P', COPY) + XX(MKCOL, 1, 'O', MOVE) + XX(MKCOL, 1, 'E', MERGE) + XX(MKCOL, 2, 'A', MKACTIVITY) + XX(MKCOL, 3, 'A', MKCALENDAR) + XX(SUBSCRIBE, 1, 'E', SEARCH) + XX(REPORT, 2, 'B', REBIND) + XX(POST, 1, 'R', PROPFIND) + XX(PROPFIND, 4, 'P', PROPPATCH) + XX(PUT, 2, 'R', PURGE) + XX(LOCK, 1, 'I', LINK) + XX(UNLOCK, 2, 'S', UNSUBSCRIBE) + XX(UNLOCK, 2, 'B', UNBIND) + XX(UNLOCK, 3, 'I', UNLINK) +#undef XX + + default: + SET_ERRNO(HPE_INVALID_METHOD); + goto error; + } + } else if (ch == '-' && + parser->index == 1 && + parser->method == HTTP_MKCOL) { + parser->method = HTTP_MSEARCH; + } else { + SET_ERRNO(HPE_INVALID_METHOD); + goto error; + } + + ++parser->index; + break; + } + + case s_req_spaces_before_url: + { + if (ch == ' ') break; + + MARK(url); + if (parser->method == HTTP_CONNECT) { + UPDATE_STATE(s_req_server_start); + } + + UPDATE_STATE(parse_url_char(CURRENT_STATE(), ch)); + if (UNLIKELY(CURRENT_STATE() == s_dead)) { + SET_ERRNO(HPE_INVALID_URL); + goto error; + } + + break; + } + + case s_req_schema: + case s_req_schema_slash: + case s_req_schema_slash_slash: + case s_req_server_start: + { + switch (ch) { + /* No whitespace allowed here */ + case ' ': + case CR: + case LF: + SET_ERRNO(HPE_INVALID_URL); + goto error; + default: + UPDATE_STATE(parse_url_char(CURRENT_STATE(), ch)); + if (UNLIKELY(CURRENT_STATE() == s_dead)) { + SET_ERRNO(HPE_INVALID_URL); + goto error; + } + } + + break; + } + + case s_req_server: + case s_req_server_with_at: + case s_req_path: + case s_req_query_string_start: + case s_req_query_string: + case s_req_fragment_start: + case s_req_fragment: + { + switch (ch) { + case ' ': + UPDATE_STATE(s_req_http_start); + CALLBACK_DATA(url); + break; + case CR: + case LF: + parser->http_major = 0; + parser->http_minor = 9; + UPDATE_STATE((ch == CR) ? + s_req_line_almost_done : + s_header_field_start); + CALLBACK_DATA(url); + break; + default: + UPDATE_STATE(parse_url_char(CURRENT_STATE(), ch)); + if (UNLIKELY(CURRENT_STATE() == s_dead)) { + SET_ERRNO(HPE_INVALID_URL); + goto error; + } + } + break; + } + + case s_req_http_start: + switch (ch) { + case 'H': + UPDATE_STATE(s_req_http_H); + break; + case ' ': + break; + default: + SET_ERRNO(HPE_INVALID_CONSTANT); + goto error; + } + break; + + case s_req_http_H: + STRICT_CHECK(ch != 'T'); + UPDATE_STATE(s_req_http_HT); + break; + + case s_req_http_HT: + STRICT_CHECK(ch != 'T'); + UPDATE_STATE(s_req_http_HTT); + break; + + case s_req_http_HTT: + STRICT_CHECK(ch != 'P'); + UPDATE_STATE(s_req_http_HTTP); + break; + + case s_req_http_HTTP: + STRICT_CHECK(ch != '/'); + UPDATE_STATE(s_req_first_http_major); + break; + + /* first digit of major HTTP version */ + case s_req_first_http_major: + if (UNLIKELY(ch < '1' || ch > '9')) { + SET_ERRNO(HPE_INVALID_VERSION); + goto error; + } + + parser->http_major = ch - '0'; + UPDATE_STATE(s_req_http_major); + break; + + /* major HTTP version or dot */ + case s_req_http_major: + { + if (ch == '.') { + UPDATE_STATE(s_req_first_http_minor); + break; + } + + if (UNLIKELY(!IS_NUM(ch))) { + SET_ERRNO(HPE_INVALID_VERSION); + goto error; + } + + parser->http_major *= 10; + parser->http_major += ch - '0'; + + if (UNLIKELY(parser->http_major > 999)) { + SET_ERRNO(HPE_INVALID_VERSION); + goto error; + } + + break; + } + + /* first digit of minor HTTP version */ + case s_req_first_http_minor: + if (UNLIKELY(!IS_NUM(ch))) { + SET_ERRNO(HPE_INVALID_VERSION); + goto error; + } + + parser->http_minor = ch - '0'; + UPDATE_STATE(s_req_http_minor); + break; + + /* minor HTTP version or end of request line */ + case s_req_http_minor: + { + if (ch == CR) { + UPDATE_STATE(s_req_line_almost_done); + break; + } + + if (ch == LF) { + UPDATE_STATE(s_header_field_start); + break; + } + + /* XXX allow spaces after digit? */ + + if (UNLIKELY(!IS_NUM(ch))) { + SET_ERRNO(HPE_INVALID_VERSION); + goto error; + } + + parser->http_minor *= 10; + parser->http_minor += ch - '0'; + + if (UNLIKELY(parser->http_minor > 999)) { + SET_ERRNO(HPE_INVALID_VERSION); + goto error; + } + + break; + } + + /* end of request line */ + case s_req_line_almost_done: + { + if (UNLIKELY(ch != LF)) { + SET_ERRNO(HPE_LF_EXPECTED); + goto error; + } + + UPDATE_STATE(s_header_field_start); + break; + } + + case s_header_field_start: + { + if (ch == CR) { + UPDATE_STATE(s_headers_almost_done); + break; + } + + if (ch == LF) { + /* they might be just sending \n instead of \r\n so this would be + * the second \n to denote the end of headers*/ + UPDATE_STATE(s_headers_almost_done); + REEXECUTE(); + } + + c = TOKEN(ch); + + if (UNLIKELY(!c)) { + SET_ERRNO(HPE_INVALID_HEADER_TOKEN); + goto error; + } + + MARK(header_field); + + parser->index = 0; + UPDATE_STATE(s_header_field); + + switch (c) { + case 'c': + parser->header_state = h_C; + break; + + case 'p': + parser->header_state = h_matching_proxy_connection; + break; + + case 't': + parser->header_state = h_matching_transfer_encoding; + break; + + case 'u': + parser->header_state = h_matching_upgrade; + break; + + default: + parser->header_state = h_general; + break; + } + break; + } + + case s_header_field: + { + const char* start = p; + for (; p != data + len; p++) { + ch = *p; + c = TOKEN(ch); + + if (!c) + break; + + switch (parser->header_state) { + case h_general: + break; + + case h_C: + parser->index++; + parser->header_state = (c == 'o' ? h_CO : h_general); + break; + + case h_CO: + parser->index++; + parser->header_state = (c == 'n' ? h_CON : h_general); + break; + + case h_CON: + parser->index++; + switch (c) { + case 'n': + parser->header_state = h_matching_connection; + break; + case 't': + parser->header_state = h_matching_content_length; + break; + default: + parser->header_state = h_general; + break; + } + break; + + /* connection */ + + case h_matching_connection: + parser->index++; + if (parser->index > sizeof(CONNECTION)-1 + || c != CONNECTION[parser->index]) { + parser->header_state = h_general; + } else if (parser->index == sizeof(CONNECTION)-2) { + parser->header_state = h_connection; + } + break; + + /* proxy-connection */ + + case h_matching_proxy_connection: + parser->index++; + if (parser->index > sizeof(PROXY_CONNECTION)-1 + || c != PROXY_CONNECTION[parser->index]) { + parser->header_state = h_general; + } else if (parser->index == sizeof(PROXY_CONNECTION)-2) { + parser->header_state = h_connection; + } + break; + + /* content-length */ + + case h_matching_content_length: + parser->index++; + if (parser->index > sizeof(CONTENT_LENGTH)-1 + || c != CONTENT_LENGTH[parser->index]) { + parser->header_state = h_general; + } else if (parser->index == sizeof(CONTENT_LENGTH)-2) { + parser->header_state = h_content_length; + } + break; + + /* transfer-encoding */ + + case h_matching_transfer_encoding: + parser->index++; + if (parser->index > sizeof(TRANSFER_ENCODING)-1 + || c != TRANSFER_ENCODING[parser->index]) { + parser->header_state = h_general; + } else if (parser->index == sizeof(TRANSFER_ENCODING)-2) { + parser->header_state = h_transfer_encoding; + } + break; + + /* upgrade */ + + case h_matching_upgrade: + parser->index++; + if (parser->index > sizeof(UPGRADE)-1 + || c != UPGRADE[parser->index]) { + parser->header_state = h_general; + } else if (parser->index == sizeof(UPGRADE)-2) { + parser->header_state = h_upgrade; + } + break; + + case h_connection: + case h_content_length: + case h_transfer_encoding: + case h_upgrade: + if (ch != ' ') parser->header_state = h_general; + break; + + default: + assert(0 && "Unknown header_state"); + break; + } + } + + COUNT_HEADER_SIZE(p - start); + + if (p == data + len) { + --p; + break; + } + + if (ch == ':') { + UPDATE_STATE(s_header_value_discard_ws); + CALLBACK_DATA(header_field); + break; + } + + SET_ERRNO(HPE_INVALID_HEADER_TOKEN); + goto error; + } + + case s_header_value_discard_ws: + if (ch == ' ' || ch == '\t') break; + + if (ch == CR) { + UPDATE_STATE(s_header_value_discard_ws_almost_done); + break; + } + + if (ch == LF) { + UPDATE_STATE(s_header_value_discard_lws); + break; + } + + /* FALLTHROUGH */ + + case s_header_value_start: + { + MARK(header_value); + + UPDATE_STATE(s_header_value); + parser->index = 0; + + c = LOWER(ch); + + switch (parser->header_state) { + case h_upgrade: + parser->flags |= F_UPGRADE; + parser->header_state = h_general; + break; + + case h_transfer_encoding: + /* looking for 'Transfer-Encoding: chunked' */ + if ('c' == c) { + parser->header_state = h_matching_transfer_encoding_chunked; + } else { + parser->header_state = h_general; + } + break; + + case h_content_length: + if (UNLIKELY(!IS_NUM(ch))) { + SET_ERRNO(HPE_INVALID_CONTENT_LENGTH); + goto error; + } + + if (parser->flags & F_CONTENTLENGTH) { + SET_ERRNO(HPE_UNEXPECTED_CONTENT_LENGTH); + goto error; + } + + parser->flags |= F_CONTENTLENGTH; + parser->content_length = ch - '0'; + break; + + case h_connection: + /* looking for 'Connection: keep-alive' */ + if (c == 'k') { + parser->header_state = h_matching_connection_keep_alive; + /* looking for 'Connection: close' */ + } else if (c == 'c') { + parser->header_state = h_matching_connection_close; + } else if (c == 'u') { + parser->header_state = h_matching_connection_upgrade; + } else { + parser->header_state = h_matching_connection_token; + } + break; + + /* Multi-value `Connection` header */ + case h_matching_connection_token_start: + break; + + default: + parser->header_state = h_general; + break; + } + break; + } + + case s_header_value: + { + const char* start = p; + enum header_states h_state = (enum header_states) parser->header_state; + for (; p != data + len; p++) { + ch = *p; + if (ch == CR) { + UPDATE_STATE(s_header_almost_done); + parser->header_state = h_state; + CALLBACK_DATA(header_value); + break; + } + + if (ch == LF) { + UPDATE_STATE(s_header_almost_done); + COUNT_HEADER_SIZE(p - start); + parser->header_state = h_state; + CALLBACK_DATA_NOADVANCE(header_value); + REEXECUTE(); + } + + if (!lenient && !IS_HEADER_CHAR(ch)) { + SET_ERRNO(HPE_INVALID_HEADER_TOKEN); + goto error; + } + + c = LOWER(ch); + + switch (h_state) { + case h_general: + { + const char* p_cr; + const char* p_lf; + uint32_t limit = data + len - p; + + limit = MIN(limit, HTTP_MAX_HEADER_SIZE); + + p_cr = (const char*) memchr(p, CR, limit); + p_lf = (const char*) memchr(p, LF, limit); + if (p_cr != NULL) { + if (p_lf != NULL && p_cr >= p_lf) + p = p_lf; + else + p = p_cr; + } else if (UNLIKELY(p_lf != NULL)) { + p = p_lf; + } else { + p = data + len; + } + --p; + + break; + } + + case h_connection: + case h_transfer_encoding: + assert(0 && "Shouldn't get here."); + break; + + case h_content_length: + { + uint64_t t; + + if (ch == ' ') break; + + if (UNLIKELY(!IS_NUM(ch))) { + SET_ERRNO(HPE_INVALID_CONTENT_LENGTH); + parser->header_state = h_state; + goto error; + } + + t = parser->content_length; + t *= 10; + t += ch - '0'; + + /* Overflow? Test against a conservative limit for simplicity. */ + if (UNLIKELY((ULLONG_MAX - 10) / 10 < parser->content_length)) { + SET_ERRNO(HPE_INVALID_CONTENT_LENGTH); + parser->header_state = h_state; + goto error; + } + + parser->content_length = t; + break; + } + + /* Transfer-Encoding: chunked */ + case h_matching_transfer_encoding_chunked: + parser->index++; + if (parser->index > sizeof(CHUNKED)-1 + || c != CHUNKED[parser->index]) { + h_state = h_general; + } else if (parser->index == sizeof(CHUNKED)-2) { + h_state = h_transfer_encoding_chunked; + } + break; + + case h_matching_connection_token_start: + /* looking for 'Connection: keep-alive' */ + if (c == 'k') { + h_state = h_matching_connection_keep_alive; + /* looking for 'Connection: close' */ + } else if (c == 'c') { + h_state = h_matching_connection_close; + } else if (c == 'u') { + h_state = h_matching_connection_upgrade; + } else if (STRICT_TOKEN(c)) { + h_state = h_matching_connection_token; + } else if (c == ' ' || c == '\t') { + /* Skip lws */ + } else { + h_state = h_general; + } + break; + + /* looking for 'Connection: keep-alive' */ + case h_matching_connection_keep_alive: + parser->index++; + if (parser->index > sizeof(KEEP_ALIVE)-1 + || c != KEEP_ALIVE[parser->index]) { + h_state = h_matching_connection_token; + } else if (parser->index == sizeof(KEEP_ALIVE)-2) { + h_state = h_connection_keep_alive; + } + break; + + /* looking for 'Connection: close' */ + case h_matching_connection_close: + parser->index++; + if (parser->index > sizeof(CLOSE)-1 || c != CLOSE[parser->index]) { + h_state = h_matching_connection_token; + } else if (parser->index == sizeof(CLOSE)-2) { + h_state = h_connection_close; + } + break; + + /* looking for 'Connection: upgrade' */ + case h_matching_connection_upgrade: + parser->index++; + if (parser->index > sizeof(UPGRADE) - 1 || + c != UPGRADE[parser->index]) { + h_state = h_matching_connection_token; + } else if (parser->index == sizeof(UPGRADE)-2) { + h_state = h_connection_upgrade; + } + break; + + case h_matching_connection_token: + if (ch == ',') { + h_state = h_matching_connection_token_start; + parser->index = 0; + } + break; + + case h_transfer_encoding_chunked: + if (ch != ' ') h_state = h_general; + break; + + case h_connection_keep_alive: + case h_connection_close: + case h_connection_upgrade: + if (ch == ',') { + if (h_state == h_connection_keep_alive) { + parser->flags |= F_CONNECTION_KEEP_ALIVE; + } else if (h_state == h_connection_close) { + parser->flags |= F_CONNECTION_CLOSE; + } else if (h_state == h_connection_upgrade) { + parser->flags |= F_CONNECTION_UPGRADE; + } + h_state = h_matching_connection_token_start; + parser->index = 0; + } else if (ch != ' ') { + h_state = h_matching_connection_token; + } + break; + + default: + UPDATE_STATE(s_header_value); + h_state = h_general; + break; + } + } + parser->header_state = h_state; + + COUNT_HEADER_SIZE(p - start); + + if (p == data + len) + --p; + break; + } + + case s_header_almost_done: + { + if (UNLIKELY(ch != LF)) { + SET_ERRNO(HPE_LF_EXPECTED); + goto error; + } + + UPDATE_STATE(s_header_value_lws); + break; + } + + case s_header_value_lws: + { + if (ch == ' ' || ch == '\t') { + UPDATE_STATE(s_header_value_start); + REEXECUTE(); + } + + /* finished the header */ + switch (parser->header_state) { + case h_connection_keep_alive: + parser->flags |= F_CONNECTION_KEEP_ALIVE; + break; + case h_connection_close: + parser->flags |= F_CONNECTION_CLOSE; + break; + case h_transfer_encoding_chunked: + parser->flags |= F_CHUNKED; + break; + case h_connection_upgrade: + parser->flags |= F_CONNECTION_UPGRADE; + break; + default: + break; + } + + UPDATE_STATE(s_header_field_start); + REEXECUTE(); + } + + case s_header_value_discard_ws_almost_done: + { + STRICT_CHECK(ch != LF); + UPDATE_STATE(s_header_value_discard_lws); + break; + } + + case s_header_value_discard_lws: + { + if (ch == ' ' || ch == '\t') { + UPDATE_STATE(s_header_value_discard_ws); + break; + } else { + switch (parser->header_state) { + case h_connection_keep_alive: + parser->flags |= F_CONNECTION_KEEP_ALIVE; + break; + case h_connection_close: + parser->flags |= F_CONNECTION_CLOSE; + break; + case h_connection_upgrade: + parser->flags |= F_CONNECTION_UPGRADE; + break; + case h_transfer_encoding_chunked: + parser->flags |= F_CHUNKED; + break; + default: + break; + } + + /* header value was empty */ + MARK(header_value); + UPDATE_STATE(s_header_field_start); + CALLBACK_DATA_NOADVANCE(header_value); + REEXECUTE(); + } + } + + case s_headers_almost_done: + { + STRICT_CHECK(ch != LF); + + if (parser->flags & F_TRAILING) { + /* End of a chunked request */ + UPDATE_STATE(s_message_done); + CALLBACK_NOTIFY_NOADVANCE(chunk_complete); + REEXECUTE(); + } + + /* Cannot use chunked encoding and a content-length header together + per the HTTP specification. */ + if ((parser->flags & F_CHUNKED) && + (parser->flags & F_CONTENTLENGTH)) { + SET_ERRNO(HPE_UNEXPECTED_CONTENT_LENGTH); + goto error; + } + + UPDATE_STATE(s_headers_done); + + /* Set this here so that on_headers_complete() callbacks can see it */ + parser->upgrade = + ((parser->flags & (F_UPGRADE | F_CONNECTION_UPGRADE)) == + (F_UPGRADE | F_CONNECTION_UPGRADE) || + parser->method == HTTP_CONNECT); + + /* Here we call the headers_complete callback. This is somewhat + * different than other callbacks because if the user returns 1, we + * will interpret that as saying that this message has no body. This + * is needed for the annoying case of recieving a response to a HEAD + * request. + * + * We'd like to use CALLBACK_NOTIFY_NOADVANCE() here but we cannot, so + * we have to simulate it by handling a change in errno below. + */ + if (settings->on_headers_complete) { + switch (settings->on_headers_complete(parser)) { + case 0: + break; + + case 2: + parser->upgrade = 1; + + case 1: + parser->flags |= F_SKIPBODY; + break; + + default: + SET_ERRNO(HPE_CB_headers_complete); + RETURN(p - data); /* Error */ + } + } + + if (HTTP_PARSER_ERRNO(parser) != HPE_OK) { + RETURN(p - data); + } + + REEXECUTE(); + } + + case s_headers_done: + { + int hasBody; + STRICT_CHECK(ch != LF); + + parser->nread = 0; + + hasBody = parser->flags & F_CHUNKED || + (parser->content_length > 0 && parser->content_length != ULLONG_MAX); + if (parser->upgrade && (parser->method == HTTP_CONNECT || + (parser->flags & F_SKIPBODY) || !hasBody)) { + /* Exit, the rest of the message is in a different protocol. */ + UPDATE_STATE(NEW_MESSAGE()); + CALLBACK_NOTIFY(message_complete); + RETURN((p - data) + 1); + } + + if (parser->flags & F_SKIPBODY) { + UPDATE_STATE(NEW_MESSAGE()); + CALLBACK_NOTIFY(message_complete); + } else if (parser->flags & F_CHUNKED) { + /* chunked encoding - ignore Content-Length header */ + UPDATE_STATE(s_chunk_size_start); + } else { + if (parser->content_length == 0) { + /* Content-Length header given but zero: Content-Length: 0\r\n */ + UPDATE_STATE(NEW_MESSAGE()); + CALLBACK_NOTIFY(message_complete); + } else if (parser->content_length != ULLONG_MAX) { + /* Content-Length header given and non-zero */ + UPDATE_STATE(s_body_identity); + } else { + if (!http_message_needs_eof(parser)) { + /* Assume content-length 0 - read the next */ + UPDATE_STATE(NEW_MESSAGE()); + CALLBACK_NOTIFY(message_complete); + } else { + /* Read body until EOF */ + UPDATE_STATE(s_body_identity_eof); + } + } + } + + break; + } + + case s_body_identity: + { + uint64_t to_read = MIN(parser->content_length, + (uint64_t) ((data + len) - p)); + + assert(parser->content_length != 0 + && parser->content_length != ULLONG_MAX); + + /* The difference between advancing content_length and p is because + * the latter will automaticaly advance on the next loop iteration. + * Further, if content_length ends up at 0, we want to see the last + * byte again for our message complete callback. + */ + MARK(body); + parser->content_length -= to_read; + p += to_read - 1; + + if (parser->content_length == 0) { + UPDATE_STATE(s_message_done); + + /* Mimic CALLBACK_DATA_NOADVANCE() but with one extra byte. + * + * The alternative to doing this is to wait for the next byte to + * trigger the data callback, just as in every other case. The + * problem with this is that this makes it difficult for the test + * harness to distinguish between complete-on-EOF and + * complete-on-length. It's not clear that this distinction is + * important for applications, but let's keep it for now. + */ + CALLBACK_DATA_(body, p - body_mark + 1, p - data); + REEXECUTE(); + } + + break; + } + + /* read until EOF */ + case s_body_identity_eof: + MARK(body); + p = data + len - 1; + + break; + + case s_message_done: + UPDATE_STATE(NEW_MESSAGE()); + CALLBACK_NOTIFY(message_complete); + if (parser->upgrade) { + /* Exit, the rest of the message is in a different protocol. */ + RETURN((p - data) + 1); + } + break; + + case s_chunk_size_start: + { + assert(parser->nread == 1); + assert(parser->flags & F_CHUNKED); + + unhex_val = unhex[(unsigned char)ch]; + if (UNLIKELY(unhex_val == -1)) { + SET_ERRNO(HPE_INVALID_CHUNK_SIZE); + goto error; + } + + parser->content_length = unhex_val; + UPDATE_STATE(s_chunk_size); + break; + } + + case s_chunk_size: + { + uint64_t t; + + assert(parser->flags & F_CHUNKED); + + if (ch == CR) { + UPDATE_STATE(s_chunk_size_almost_done); + break; + } + + unhex_val = unhex[(unsigned char)ch]; + + if (unhex_val == -1) { + if (ch == ';' || ch == ' ') { + UPDATE_STATE(s_chunk_parameters); + break; + } + + SET_ERRNO(HPE_INVALID_CHUNK_SIZE); + goto error; + } + + t = parser->content_length; + t *= 16; + t += unhex_val; + + /* Overflow? Test against a conservative limit for simplicity. */ + if (UNLIKELY((ULLONG_MAX - 16) / 16 < parser->content_length)) { + SET_ERRNO(HPE_INVALID_CONTENT_LENGTH); + goto error; + } + + parser->content_length = t; + break; + } + + case s_chunk_parameters: + { + assert(parser->flags & F_CHUNKED); + /* just ignore this shit. TODO check for overflow */ + if (ch == CR) { + UPDATE_STATE(s_chunk_size_almost_done); + break; + } + break; + } + + case s_chunk_size_almost_done: + { + assert(parser->flags & F_CHUNKED); + STRICT_CHECK(ch != LF); + + parser->nread = 0; + + if (parser->content_length == 0) { + parser->flags |= F_TRAILING; + UPDATE_STATE(s_header_field_start); + } else { + UPDATE_STATE(s_chunk_data); + } + CALLBACK_NOTIFY(chunk_header); + break; + } + + case s_chunk_data: + { + uint64_t to_read = MIN(parser->content_length, + (uint64_t) ((data + len) - p)); + + assert(parser->flags & F_CHUNKED); + assert(parser->content_length != 0 + && parser->content_length != ULLONG_MAX); + + /* See the explanation in s_body_identity for why the content + * length and data pointers are managed this way. + */ + MARK(body); + parser->content_length -= to_read; + p += to_read - 1; + + if (parser->content_length == 0) { + UPDATE_STATE(s_chunk_data_almost_done); + } + + break; + } + + case s_chunk_data_almost_done: + assert(parser->flags & F_CHUNKED); + assert(parser->content_length == 0); + STRICT_CHECK(ch != CR); + UPDATE_STATE(s_chunk_data_done); + CALLBACK_DATA(body); + break; + + case s_chunk_data_done: + assert(parser->flags & F_CHUNKED); + STRICT_CHECK(ch != LF); + parser->nread = 0; + UPDATE_STATE(s_chunk_size_start); + CALLBACK_NOTIFY(chunk_complete); + break; + + default: + assert(0 && "unhandled state"); + SET_ERRNO(HPE_INVALID_INTERNAL_STATE); + goto error; + } + } + + /* Run callbacks for any marks that we have leftover after we ran our of + * bytes. There should be at most one of these set, so it's OK to invoke + * them in series (unset marks will not result in callbacks). + * + * We use the NOADVANCE() variety of callbacks here because 'p' has already + * overflowed 'data' and this allows us to correct for the off-by-one that + * we'd otherwise have (since CALLBACK_DATA() is meant to be run with a 'p' + * value that's in-bounds). + */ + + assert(((header_field_mark ? 1 : 0) + + (header_value_mark ? 1 : 0) + + (url_mark ? 1 : 0) + + (body_mark ? 1 : 0) + + (status_mark ? 1 : 0)) <= 1); + + CALLBACK_DATA_NOADVANCE(header_field); + CALLBACK_DATA_NOADVANCE(header_value); + CALLBACK_DATA_NOADVANCE(url); + CALLBACK_DATA_NOADVANCE(body); + CALLBACK_DATA_NOADVANCE(status); + + RETURN(len); + +error: + if (HTTP_PARSER_ERRNO(parser) == HPE_OK) { + SET_ERRNO(HPE_UNKNOWN); + } + + RETURN(p - data); +} + + +/* Does the parser need to see an EOF to find the end of the message? */ +int +http_message_needs_eof (const http_parser *parser) +{ + if (parser->type == HTTP_REQUEST) { + return 0; + } + + /* See RFC 2616 section 4.4 */ + if (parser->status_code / 100 == 1 || /* 1xx e.g. Continue */ + parser->status_code == 204 || /* No Content */ + parser->status_code == 304 || /* Not Modified */ + parser->flags & F_SKIPBODY) { /* response to a HEAD request */ + return 0; + } + + if ((parser->flags & F_CHUNKED) || parser->content_length != ULLONG_MAX) { + return 0; + } + + return 1; +} + + +int +http_should_keep_alive (const http_parser *parser) +{ + if (parser->http_major > 0 && parser->http_minor > 0) { + /* HTTP/1.1 */ + if (parser->flags & F_CONNECTION_CLOSE) { + return 0; + } + } else { + /* HTTP/1.0 or earlier */ + if (!(parser->flags & F_CONNECTION_KEEP_ALIVE)) { + return 0; + } + } + + return !http_message_needs_eof(parser); +} + + +const char * +http_method_str (enum http_method m) +{ + return ELEM_AT(method_strings, m, ""); +} + + +void +http_parser_init (http_parser *parser, enum http_parser_type t) +{ + void *data = parser->data; /* preserve application data */ + memset(parser, 0, sizeof(*parser)); + parser->data = data; + parser->type = t; + parser->state = (t == HTTP_REQUEST ? s_start_req : (t == HTTP_RESPONSE ? s_start_res : s_start_req_or_res)); + parser->http_errno = HPE_OK; +} + +void +http_parser_settings_init(http_parser_settings *settings) +{ + memset(settings, 0, sizeof(*settings)); +} + +const char * +http_errno_name(enum http_errno err) { + assert(((uint32_t) err) < ARRAY_SIZE(http_strerror_tab)); + return http_strerror_tab[err].name; +} + +const char * +http_errno_description(enum http_errno err) { + assert(((uint32_t) err) < ARRAY_SIZE(http_strerror_tab)); + return http_strerror_tab[err].description; +} + +static enum http_host_state +http_parse_host_char(enum http_host_state s, const char ch) { + switch(s) { + case s_http_userinfo: + case s_http_userinfo_start: + if (ch == '@') { + return s_http_host_start; + } + + if (IS_USERINFO_CHAR(ch)) { + return s_http_userinfo; + } + break; + + case s_http_host_start: + if (ch == '[') { + return s_http_host_v6_start; + } + + if (IS_HOST_CHAR(ch)) { + return s_http_host; + } + + break; + + case s_http_host: + if (IS_HOST_CHAR(ch)) { + return s_http_host; + } + + /* FALLTHROUGH */ + case s_http_host_v6_end: + if (ch == ':') { + return s_http_host_port_start; + } + + break; + + case s_http_host_v6: + if (ch == ']') { + return s_http_host_v6_end; + } + + /* FALLTHROUGH */ + case s_http_host_v6_start: + if (IS_HEX(ch) || ch == ':' || ch == '.') { + return s_http_host_v6; + } + + if (s == s_http_host_v6 && ch == '%') { + return s_http_host_v6_zone_start; + } + break; + + case s_http_host_v6_zone: + if (ch == ']') { + return s_http_host_v6_end; + } + + /* FALLTHROUGH */ + case s_http_host_v6_zone_start: + /* RFC 6874 Zone ID consists of 1*( unreserved / pct-encoded) */ + if (IS_ALPHANUM(ch) || ch == '%' || ch == '.' || ch == '-' || ch == '_' || + ch == '~') { + return s_http_host_v6_zone; + } + break; + + case s_http_host_port: + case s_http_host_port_start: + if (IS_NUM(ch)) { + return s_http_host_port; + } + + break; + + default: + break; + } + return s_http_host_dead; +} + +static int +http_parse_host(const char * buf, struct http_parser_url *u, int found_at) { + enum http_host_state s; + + const char *p; + uint32_t buflen = u->field_data[UF_HOST].off + u->field_data[UF_HOST].len; + + assert(u->field_set & (1 << UF_HOST)); + + u->field_data[UF_HOST].len = 0; + + s = found_at ? s_http_userinfo_start : s_http_host_start; + + for (p = buf + u->field_data[UF_HOST].off; p < buf + buflen; p++) { + enum http_host_state new_s = http_parse_host_char(s, *p); + + if (new_s == s_http_host_dead) { + return 1; + } + + switch(new_s) { + case s_http_host: + if (s != s_http_host) { + u->field_data[UF_HOST].off = p - buf; + } + u->field_data[UF_HOST].len++; + break; + + case s_http_host_v6: + if (s != s_http_host_v6) { + u->field_data[UF_HOST].off = p - buf; + } + u->field_data[UF_HOST].len++; + break; + + case s_http_host_v6_zone_start: + case s_http_host_v6_zone: + u->field_data[UF_HOST].len++; + break; + + case s_http_host_port: + if (s != s_http_host_port) { + u->field_data[UF_PORT].off = p - buf; + u->field_data[UF_PORT].len = 0; + u->field_set |= (1 << UF_PORT); + } + u->field_data[UF_PORT].len++; + break; + + case s_http_userinfo: + if (s != s_http_userinfo) { + u->field_data[UF_USERINFO].off = p - buf ; + u->field_data[UF_USERINFO].len = 0; + u->field_set |= (1 << UF_USERINFO); + } + u->field_data[UF_USERINFO].len++; + break; + + default: + break; + } + s = new_s; + } + + /* Make sure we don't end somewhere unexpected */ + switch (s) { + case s_http_host_start: + case s_http_host_v6_start: + case s_http_host_v6: + case s_http_host_v6_zone_start: + case s_http_host_v6_zone: + case s_http_host_port_start: + case s_http_userinfo: + case s_http_userinfo_start: + return 1; + default: + break; + } + + return 0; +} + +void +http_parser_url_init(struct http_parser_url *u) { + memset(u, 0, sizeof(*u)); +} + +int +http_parser_parse_url(const char *buf, uint32_t buflen, int is_connect, + struct http_parser_url *u) +{ + enum state s; + const char *p; + enum http_parser_url_fields uf, old_uf; + int found_at = 0; + + u->port = u->field_set = 0; + s = is_connect ? s_req_server_start : s_req_spaces_before_url; + old_uf = UF_MAX; + + for (p = buf; p < buf + buflen; p++) { + s = parse_url_char(s, *p); + + /* Figure out the next field that we're operating on */ + switch (s) { + case s_dead: + return 1; + + /* Skip delimeters */ + case s_req_schema_slash: + case s_req_schema_slash_slash: + case s_req_server_start: + case s_req_query_string_start: + case s_req_fragment_start: + continue; + + case s_req_schema: + uf = UF_SCHEMA; + break; + + case s_req_server_with_at: + found_at = 1; + + /* FALLTROUGH */ + case s_req_server: + uf = UF_HOST; + break; + + case s_req_path: + uf = UF_PATH; + break; + + case s_req_query_string: + uf = UF_QUERY; + break; + + case s_req_fragment: + uf = UF_FRAGMENT; + break; + + default: + assert(!"Unexpected state"); + return 1; + } + + /* Nothing's changed; soldier on */ + if (uf == old_uf) { + u->field_data[uf].len++; + continue; + } + + u->field_data[uf].off = p - buf; + u->field_data[uf].len = 1; + + u->field_set |= (1 << uf); + old_uf = uf; + } + + /* host must be present if there is a schema */ + /* parsing http:///toto will fail */ + if ((u->field_set & (1 << UF_SCHEMA)) && + (u->field_set & (1 << UF_HOST)) == 0) { + return 1; + } + + if (u->field_set & (1 << UF_HOST)) { + if (http_parse_host(buf, u, found_at) != 0) { + return 1; + } + } + + /* CONNECT requests can only contain "hostname:port" */ + if (is_connect && u->field_set != ((1 << UF_HOST)|(1 << UF_PORT))) { + return 1; + } + + if (u->field_set & (1 << UF_PORT)) { + /* Don't bother with endp; we've already validated the string */ + unsigned long v = strtoul(buf + u->field_data[UF_PORT].off, NULL, 10); + + /* Ports have a max value of 2^16 */ + if (v > 0xffff) { + return 1; + } + + u->port = (uint16_t) v; + } + + return 0; +} + +void +http_parser_pause(http_parser *parser, int paused) { + /* Users should only be pausing/unpausing a parser that is not in an error + * state. In non-debug builds, there's not much that we can do about this + * other than ignore it. + */ + if (HTTP_PARSER_ERRNO(parser) == HPE_OK || + HTTP_PARSER_ERRNO(parser) == HPE_PAUSED) { + SET_ERRNO((paused) ? HPE_PAUSED : HPE_OK); + } else { + assert(0 && "Attempting to pause parser in error state"); + } +} + +int +http_body_is_final(const struct http_parser *parser) { + return parser->state == s_message_done; +} + +unsigned long +http_parser_version(void) { + return HTTP_PARSER_VERSION_MAJOR * 0x10000 | + HTTP_PARSER_VERSION_MINOR * 0x00100 | + HTTP_PARSER_VERSION_PATCH * 0x00001; +} diff --git a/src/utility/http_parser.h b/src/utility/http_parser.h new file mode 100644 index 0000000..472bf54 --- /dev/null +++ b/src/utility/http_parser.h @@ -0,0 +1,432 @@ +/* Copyright Joyent, Inc. and other Node contributors. All rights reserved. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to + * deal in the Software without restriction, including without limitation the + * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ +#ifndef http_parser_h +#define http_parser_h + +#ifdef __cplusplus +extern "C" { +#endif + +/* Also update SONAME in the Makefile whenever you change these. */ +#define HTTP_PARSER_VERSION_MAJOR 2 +#define HTTP_PARSER_VERSION_MINOR 7 +#define HTTP_PARSER_VERSION_PATCH 1 + +#if defined(_WIN32) && !defined(__MINGW32__) && \ + (!defined(_MSC_VER) || _MSC_VER<1600) && !defined(__WINE__) +#include +#include +typedef __int8 int8_t; +typedef unsigned __int8 uint8_t; +typedef __int16 int16_t; +typedef unsigned __int16 uint16_t; +typedef __int32 int32_t; +typedef unsigned __int32 uint32_t; +typedef __int64 int64_t; +typedef unsigned __int64 uint64_t; +#else +#include +#endif + +/* Compile with -DHTTP_PARSER_STRICT=0 to make less checks, but run + * faster + */ +#ifndef HTTP_PARSER_STRICT +# define HTTP_PARSER_STRICT 1 +#endif + +/* Maximium header size allowed. If the macro is not defined + * before including this header then the default is used. To + * change the maximum header size, define the macro in the build + * environment (e.g. -DHTTP_MAX_HEADER_SIZE=). To remove + * the effective limit on the size of the header, define the macro + * to a very large number (e.g. -DHTTP_MAX_HEADER_SIZE=0x7fffffff) + */ +#ifndef HTTP_MAX_HEADER_SIZE +# define HTTP_MAX_HEADER_SIZE (80*1024) +#endif + +typedef struct http_parser http_parser; +typedef struct http_parser_settings http_parser_settings; + + +/* Callbacks should return non-zero to indicate an error. The parser will + * then halt execution. + * + * The one exception is on_headers_complete. In a HTTP_RESPONSE parser + * returning '1' from on_headers_complete will tell the parser that it + * should not expect a body. This is used when receiving a response to a + * HEAD request which may contain 'Content-Length' or 'Transfer-Encoding: + * chunked' headers that indicate the presence of a body. + * + * Returning `2` from on_headers_complete will tell parser that it should not + * expect neither a body nor any futher responses on this connection. This is + * useful for handling responses to a CONNECT request which may not contain + * `Upgrade` or `Connection: upgrade` headers. + * + * http_data_cb does not return data chunks. It will be called arbitrarily + * many times for each string. E.G. you might get 10 callbacks for "on_url" + * each providing just a few characters more data. + */ +typedef int (*http_data_cb) (http_parser*, const char *at, uint32_t length); +typedef int (*http_cb) (http_parser*); + + +/* Status Codes */ +#define HTTP_STATUS_MAP(XX) \ + XX(100, CONTINUE, Continue) \ + XX(101, SWITCHING_PROTOCOLS, Switching Protocols) \ + XX(102, PROCESSING, Processing) \ + XX(200, OK, OK) \ + XX(201, CREATED, Created) \ + XX(202, ACCEPTED, Accepted) \ + XX(203, NON_AUTHORITATIVE_INFORMATION, Non-Authoritative Information) \ + XX(204, NO_CONTENT, No Content) \ + XX(205, RESET_CONTENT, Reset Content) \ + XX(206, PARTIAL_CONTENT, Partial Content) \ + XX(207, MULTI_STATUS, Multi-Status) \ + XX(208, ALREADY_REPORTED, Already Reported) \ + XX(226, IM_USED, IM Used) \ + XX(300, MULTIPLE_CHOICES, Multiple Choices) \ + XX(301, MOVED_PERMANENTLY, Moved Permanently) \ + XX(302, FOUND, Found) \ + XX(303, SEE_OTHER, See Other) \ + XX(304, NOT_MODIFIED, Not Modified) \ + XX(305, USE_PROXY, Use Proxy) \ + XX(307, TEMPORARY_REDIRECT, Temporary Redirect) \ + XX(308, PERMANENT_REDIRECT, Permanent Redirect) \ + XX(400, BAD_REQUEST, Bad Request) \ + XX(401, UNAUTHORIZED, Unauthorized) \ + XX(402, PAYMENT_REQUIRED, Payment Required) \ + XX(403, FORBIDDEN, Forbidden) \ + XX(404, NOT_FOUND, Not Found) \ + XX(405, METHOD_NOT_ALLOWED, Method Not Allowed) \ + XX(406, NOT_ACCEPTABLE, Not Acceptable) \ + XX(407, PROXY_AUTHENTICATION_REQUIRED, Proxy Authentication Required) \ + XX(408, REQUEST_TIMEOUT, Request Timeout) \ + XX(409, CONFLICT, Conflict) \ + XX(410, GONE, Gone) \ + XX(411, LENGTH_REQUIRED, Length Required) \ + XX(412, PRECONDITION_FAILED, Precondition Failed) \ + XX(413, PAYLOAD_TOO_LARGE, Payload Too Large) \ + XX(414, URI_TOO_LONG, URI Too Long) \ + XX(415, UNSUPPORTED_MEDIA_TYPE, Unsupported Media Type) \ + XX(416, RANGE_NOT_SATISFIABLE, Range Not Satisfiable) \ + XX(417, EXPECTATION_FAILED, Expectation Failed) \ + XX(421, MISDIRECTED_REQUEST, Misdirected Request) \ + XX(422, UNPROCESSABLE_ENTITY, Unprocessable Entity) \ + XX(423, LOCKED, Locked) \ + XX(424, FAILED_DEPENDENCY, Failed Dependency) \ + XX(426, UPGRADE_REQUIRED, Upgrade Required) \ + XX(428, PRECONDITION_REQUIRED, Precondition Required) \ + XX(429, TOO_MANY_REQUESTS, Too Many Requests) \ + XX(431, REQUEST_HEADER_FIELDS_TOO_LARGE, Request Header Fields Too Large) \ + XX(451, UNAVAILABLE_FOR_LEGAL_REASONS, Unavailable For Legal Reasons) \ + XX(500, INTERNAL_SERVER_ERROR, Internal Server Error) \ + XX(501, NOT_IMPLEMENTED, Not Implemented) \ + XX(502, BAD_GATEWAY, Bad Gateway) \ + XX(503, SERVICE_UNAVAILABLE, Service Unavailable) \ + XX(504, GATEWAY_TIMEOUT, Gateway Timeout) \ + XX(505, HTTP_VERSION_NOT_SUPPORTED, HTTP Version Not Supported) \ + XX(506, VARIANT_ALSO_NEGOTIATES, Variant Also Negotiates) \ + XX(507, INSUFFICIENT_STORAGE, Insufficient Storage) \ + XX(508, LOOP_DETECTED, Loop Detected) \ + XX(510, NOT_EXTENDED, Not Extended) \ + XX(511, NETWORK_AUTHENTICATION_REQUIRED, Network Authentication Required) \ + +enum http_status + { +#define XX(num, name, string) HTTP_STATUS_##name = num, + HTTP_STATUS_MAP(XX) +#undef XX + }; + + +/* Request Methods */ +#define HTTP_METHOD_MAP(XX) \ + XX(0, DELETE, DELETE) \ + XX(1, GET, GET) \ + XX(2, HEAD, HEAD) \ + XX(3, POST, POST) \ + XX(4, PUT, PUT) \ + /* pathological */ \ + XX(5, CONNECT, CONNECT) \ + XX(6, OPTIONS, OPTIONS) \ + XX(7, TRACE, TRACE) \ + /* WebDAV */ \ + XX(8, COPY, COPY) \ + XX(9, LOCK, LOCK) \ + XX(10, MKCOL, MKCOL) \ + XX(11, MOVE, MOVE) \ + XX(12, PROPFIND, PROPFIND) \ + XX(13, PROPPATCH, PROPPATCH) \ + XX(14, SEARCH, SEARCH) \ + XX(15, UNLOCK, UNLOCK) \ + XX(16, BIND, BIND) \ + XX(17, REBIND, REBIND) \ + XX(18, UNBIND, UNBIND) \ + XX(19, ACL, ACL) \ + /* subversion */ \ + XX(20, REPORT, REPORT) \ + XX(21, MKACTIVITY, MKACTIVITY) \ + XX(22, CHECKOUT, CHECKOUT) \ + XX(23, MERGE, MERGE) \ + /* upnp */ \ + XX(24, MSEARCH, M-SEARCH) \ + XX(25, NOTIFY, NOTIFY) \ + XX(26, SUBSCRIBE, SUBSCRIBE) \ + XX(27, UNSUBSCRIBE, UNSUBSCRIBE) \ + /* RFC-5789 */ \ + XX(28, PATCH, PATCH) \ + XX(29, PURGE, PURGE) \ + /* CalDAV */ \ + XX(30, MKCALENDAR, MKCALENDAR) \ + /* RFC-2068, section 19.6.1.2 */ \ + XX(31, LINK, LINK) \ + XX(32, UNLINK, UNLINK) \ + +enum http_method + { +#define XX(num, name, string) HTTP_##name = num, + HTTP_METHOD_MAP(XX) +#undef XX + }; + + +enum http_parser_type { HTTP_REQUEST, HTTP_RESPONSE, HTTP_BOTH }; + + +/* Flag values for http_parser.flags field */ +enum flags + { F_CHUNKED = 1 << 0 + , F_CONNECTION_KEEP_ALIVE = 1 << 1 + , F_CONNECTION_CLOSE = 1 << 2 + , F_CONNECTION_UPGRADE = 1 << 3 + , F_TRAILING = 1 << 4 + , F_UPGRADE = 1 << 5 + , F_SKIPBODY = 1 << 6 + , F_CONTENTLENGTH = 1 << 7 + }; + + +/* Map for errno-related constants + * + * The provided argument should be a macro that takes 2 arguments. + */ +#define HTTP_ERRNO_MAP(XX) \ + /* No error */ \ + XX(OK, "success") \ + \ + /* Callback-related errors */ \ + XX(CB_message_begin, "the on_message_begin callback failed") \ + XX(CB_url, "the on_url callback failed") \ + XX(CB_header_field, "the on_header_field callback failed") \ + XX(CB_header_value, "the on_header_value callback failed") \ + XX(CB_headers_complete, "the on_headers_complete callback failed") \ + XX(CB_body, "the on_body callback failed") \ + XX(CB_message_complete, "the on_message_complete callback failed") \ + XX(CB_status, "the on_status callback failed") \ + XX(CB_chunk_header, "the on_chunk_header callback failed") \ + XX(CB_chunk_complete, "the on_chunk_complete callback failed") \ + \ + /* Parsing-related errors */ \ + XX(INVALID_EOF_STATE, "stream ended at an unexpected time") \ + XX(HEADER_OVERFLOW, \ + "too many header bytes seen; overflow detected") \ + XX(CLOSED_CONNECTION, \ + "data received after completed connection: close message") \ + XX(INVALID_VERSION, "invalid HTTP version") \ + XX(INVALID_STATUS, "invalid HTTP status code") \ + XX(INVALID_METHOD, "invalid HTTP method") \ + XX(INVALID_URL, "invalid URL") \ + XX(INVALID_HOST, "invalid host") \ + XX(INVALID_PORT, "invalid port") \ + XX(INVALID_PATH, "invalid path") \ + XX(INVALID_QUERY_STRING, "invalid query string") \ + XX(INVALID_FRAGMENT, "invalid fragment") \ + XX(LF_EXPECTED, "LF character expected") \ + XX(INVALID_HEADER_TOKEN, "invalid character in header") \ + XX(INVALID_CONTENT_LENGTH, \ + "invalid character in content-length header") \ + XX(UNEXPECTED_CONTENT_LENGTH, \ + "unexpected content-length header") \ + XX(INVALID_CHUNK_SIZE, \ + "invalid character in chunk size header") \ + XX(INVALID_CONSTANT, "invalid constant string") \ + XX(INVALID_INTERNAL_STATE, "encountered unexpected internal state")\ + XX(STRICT, "strict mode assertion failed") \ + XX(PAUSED, "parser is paused") \ + XX(UNKNOWN, "an unknown error occurred") + + +/* Define HPE_* values for each errno value above */ +#define HTTP_ERRNO_GEN(n, s) HPE_##n, +enum http_errno { + HTTP_ERRNO_MAP(HTTP_ERRNO_GEN) +}; +#undef HTTP_ERRNO_GEN + + +/* Get an http_errno value from an http_parser */ +#define HTTP_PARSER_ERRNO(p) ((enum http_errno) (p)->http_errno) + + +struct http_parser { + /** PRIVATE **/ + unsigned int type : 2; /* enum http_parser_type */ + unsigned int flags : 8; /* F_* values from 'flags' enum; semi-public */ + unsigned int state : 7; /* enum state from http_parser.c */ + unsigned int header_state : 7; /* enum header_state from http_parser.c */ + unsigned int index : 7; /* index into current matcher */ + unsigned int lenient_http_headers : 1; + + uint32_t nread; /* # bytes read in various scenarios */ + uint64_t content_length; /* # bytes in body (0 if no Content-Length header) */ + + /** READ-ONLY **/ + unsigned short http_major; + unsigned short http_minor; + unsigned int status_code : 16; /* responses only */ + unsigned int method : 8; /* requests only */ + unsigned int http_errno : 7; + + /* 1 = Upgrade header was present and the parser has exited because of that. + * 0 = No upgrade header present. + * Should be checked when http_parser_execute() returns in addition to + * error checking. + */ + unsigned int upgrade : 1; + + /** PUBLIC **/ + void *data; /* A pointer to get hook to the "connection" or "socket" object */ +}; + + +struct http_parser_settings { + http_cb on_message_begin; + http_data_cb on_url; + http_data_cb on_status; + http_data_cb on_header_field; + http_data_cb on_header_value; + http_cb on_headers_complete; + http_data_cb on_body; + http_cb on_message_complete; + /* When on_chunk_header is called, the current chunk length is stored + * in parser->content_length. + */ + http_cb on_chunk_header; + http_cb on_chunk_complete; +}; + + +enum http_parser_url_fields + { UF_SCHEMA = 0 + , UF_HOST = 1 + , UF_PORT = 2 + , UF_PATH = 3 + , UF_QUERY = 4 + , UF_FRAGMENT = 5 + , UF_USERINFO = 6 + , UF_MAX = 7 + }; + + +/* Result structure for http_parser_parse_url(). + * + * Callers should index into field_data[] with UF_* values iff field_set + * has the relevant (1 << UF_*) bit set. As a courtesy to clients (and + * because we probably have padding left over), we convert any port to + * a uint16_t. + */ +struct http_parser_url { + uint16_t field_set; /* Bitmask of (1 << UF_*) values */ + uint16_t port; /* Converted UF_PORT string */ + + struct { + uint16_t off; /* Offset into buffer in which field starts */ + uint16_t len; /* Length of run in buffer */ + } field_data[UF_MAX]; +}; + + +/* Returns the library version. Bits 16-23 contain the major version number, + * bits 8-15 the minor version number and bits 0-7 the patch level. + * Usage example: + * + * unsigned long version = http_parser_version(); + * unsigned major = (version >> 16) & 255; + * unsigned minor = (version >> 8) & 255; + * unsigned patch = version & 255; + * printf("http_parser v%u.%u.%u\n", major, minor, patch); + */ +unsigned long http_parser_version(void); + +void http_parser_init(http_parser *parser, enum http_parser_type type); + + +/* Initialize http_parser_settings members to 0 + */ +void http_parser_settings_init(http_parser_settings *settings); + + +/* Executes the parser. Returns number of parsed bytes. Sets + * `parser->http_errno` on error. */ +uint32_t http_parser_execute(http_parser *parser, + const http_parser_settings *settings, + const char *data, + uint32_t len); + + +/* If http_should_keep_alive() in the on_headers_complete or + * on_message_complete callback returns 0, then this should be + * the last message on the connection. + * If you are the server, respond with the "Connection: close" header. + * If you are the client, close the connection. + */ +int http_should_keep_alive(const http_parser *parser); + +/* Returns a string version of the HTTP method. */ +const char *http_method_str(enum http_method m); + +/* Return a string name of the given error */ +const char *http_errno_name(enum http_errno err); + +/* Return a string description of the given error */ +const char *http_errno_description(enum http_errno err); + +/* Initialize all http_parser_url members to 0 */ +void http_parser_url_init(struct http_parser_url *u); + +/* Parse a URL; return nonzero on failure */ +int http_parser_parse_url(const char *buf, uint32_t buflen, + int is_connect, + struct http_parser_url *u); + +/* Pause or un-pause the parser; a nonzero value pauses */ +void http_parser_pause(http_parser *parser, int paused); + +/* Checks if this is the final chunk of the body. */ +int http_body_is_final(const http_parser *parser); + +#ifdef __cplusplus +} +#endif +#endif \ No newline at end of file From 6159db90b9a4959f574a2adb4e32885ae99f6d21 Mon Sep 17 00:00:00 2001 From: Andrea Gilardoni Date: Wed, 21 Feb 2024 15:30:34 +0100 Subject: [PATCH 36/50] Removed functionalities not related to URL parsing from the imported library --- src/utility/http_parser.c | 1888 ------------------------------------- src/utility/http_parser.h | 336 ------- 2 files changed, 2224 deletions(-) diff --git a/src/utility/http_parser.c b/src/utility/http_parser.c index b6bd43e..f1be647 100644 --- a/src/utility/http_parser.c +++ b/src/utility/http_parser.c @@ -29,210 +29,17 @@ #include #include -#ifndef ULLONG_MAX -# define ULLONG_MAX ((uint64_t) -1) /* 2^64-1 */ -#endif - -#ifndef MIN -# define MIN(a,b) ((a) < (b) ? (a) : (b)) -#endif - -#ifndef ARRAY_SIZE -# define ARRAY_SIZE(a) (sizeof(a) / sizeof((a)[0])) -#endif - #ifndef BIT_AT # define BIT_AT(a, i) \ (!!((unsigned int) (a)[(unsigned int) (i) >> 3] & \ (1 << ((unsigned int) (i) & 7)))) #endif -#ifndef ELEM_AT -# define ELEM_AT(a, i, v) ((unsigned int) (i) < ARRAY_SIZE(a) ? (a)[(i)] : (v)) -#endif - #define SET_ERRNO(e) \ do { \ parser->http_errno = (e); \ } while(0) -#define CURRENT_STATE() p_state -#define UPDATE_STATE(V) p_state = (enum state) (V); -#define RETURN(V) \ -do { \ - parser->state = CURRENT_STATE(); \ - return (V); \ -} while (0); -#define REEXECUTE() \ - goto reexecute; \ - - -#ifdef __GNUC__ -# define LIKELY(X) __builtin_expect(!!(X), 1) -# define UNLIKELY(X) __builtin_expect(!!(X), 0) -#else -# define LIKELY(X) (X) -# define UNLIKELY(X) (X) -#endif - - -/* Run the notify callback FOR, returning ER if it fails */ -#define CALLBACK_NOTIFY_(FOR, ER) \ -do { \ - assert(HTTP_PARSER_ERRNO(parser) == HPE_OK); \ - \ - if (LIKELY(settings->on_##FOR)) { \ - parser->state = CURRENT_STATE(); \ - if (UNLIKELY(0 != settings->on_##FOR(parser))) { \ - SET_ERRNO(HPE_CB_##FOR); \ - } \ - UPDATE_STATE(parser->state); \ - \ - /* We either errored above or got paused; get out */ \ - if (UNLIKELY(HTTP_PARSER_ERRNO(parser) != HPE_OK)) { \ - return (ER); \ - } \ - } \ -} while (0) - -/* Run the notify callback FOR and consume the current byte */ -#define CALLBACK_NOTIFY(FOR) CALLBACK_NOTIFY_(FOR, p - data + 1) - -/* Run the notify callback FOR and don't consume the current byte */ -#define CALLBACK_NOTIFY_NOADVANCE(FOR) CALLBACK_NOTIFY_(FOR, p - data) - -/* Run data callback FOR with LEN bytes, returning ER if it fails */ -#define CALLBACK_DATA_(FOR, LEN, ER) \ -do { \ - assert(HTTP_PARSER_ERRNO(parser) == HPE_OK); \ - \ - if (FOR##_mark) { \ - if (LIKELY(settings->on_##FOR)) { \ - parser->state = CURRENT_STATE(); \ - if (UNLIKELY(0 != \ - settings->on_##FOR(parser, FOR##_mark, (LEN)))) { \ - SET_ERRNO(HPE_CB_##FOR); \ - } \ - UPDATE_STATE(parser->state); \ - \ - /* We either errored above or got paused; get out */ \ - if (UNLIKELY(HTTP_PARSER_ERRNO(parser) != HPE_OK)) { \ - return (ER); \ - } \ - } \ - FOR##_mark = NULL; \ - } \ -} while (0) - -/* Run the data callback FOR and consume the current byte */ -#define CALLBACK_DATA(FOR) \ - CALLBACK_DATA_(FOR, p - FOR##_mark, p - data + 1) - -/* Run the data callback FOR and don't consume the current byte */ -#define CALLBACK_DATA_NOADVANCE(FOR) \ - CALLBACK_DATA_(FOR, p - FOR##_mark, p - data) - -/* Set the mark FOR; non-destructive if mark is already set */ -#define MARK(FOR) \ -do { \ - if (!FOR##_mark) { \ - FOR##_mark = p; \ - } \ -} while (0) - -/* Don't allow the total size of the HTTP headers (including the status - * line) to exceed HTTP_MAX_HEADER_SIZE. This check is here to protect - * embedders against denial-of-service attacks where the attacker feeds - * us a never-ending header that the embedder keeps buffering. - * - * This check is arguably the responsibility of embedders but we're doing - * it on the embedder's behalf because most won't bother and this way we - * make the web a little safer. HTTP_MAX_HEADER_SIZE is still far bigger - * than any reasonable request or response so this should never affect - * day-to-day operation. - */ -#define COUNT_HEADER_SIZE(V) \ -do { \ - parser->nread += (V); \ - if (UNLIKELY(parser->nread > (HTTP_MAX_HEADER_SIZE))) { \ - SET_ERRNO(HPE_HEADER_OVERFLOW); \ - goto error; \ - } \ -} while (0) - - -#define PROXY_CONNECTION "proxy-connection" -#define CONNECTION "connection" -#define CONTENT_LENGTH "content-length" -#define TRANSFER_ENCODING "transfer-encoding" -#define UPGRADE "upgrade" -#define CHUNKED "chunked" -#define KEEP_ALIVE "keep-alive" -#define CLOSE "close" - - -static const char *method_strings[] = - { -#define XX(num, name, string) #string, - HTTP_METHOD_MAP(XX) -#undef XX - }; - - -/* Tokens as defined by rfc 2616. Also lowercases them. - * token = 1* - * separators = "(" | ")" | "<" | ">" | "@" - * | "," | ";" | ":" | "\" | <"> - * | "/" | "[" | "]" | "?" | "=" - * | "{" | "}" | SP | HT - */ -static const char tokens[256] = { -/* 0 nul 1 soh 2 stx 3 etx 4 eot 5 enq 6 ack 7 bel */ - 0, 0, 0, 0, 0, 0, 0, 0, -/* 8 bs 9 ht 10 nl 11 vt 12 np 13 cr 14 so 15 si */ - 0, 0, 0, 0, 0, 0, 0, 0, -/* 16 dle 17 dc1 18 dc2 19 dc3 20 dc4 21 nak 22 syn 23 etb */ - 0, 0, 0, 0, 0, 0, 0, 0, -/* 24 can 25 em 26 sub 27 esc 28 fs 29 gs 30 rs 31 us */ - 0, 0, 0, 0, 0, 0, 0, 0, -/* 32 sp 33 ! 34 " 35 # 36 $ 37 % 38 & 39 ' */ - 0, '!', 0, '#', '$', '%', '&', '\'', -/* 40 ( 41 ) 42 * 43 + 44 , 45 - 46 . 47 / */ - 0, 0, '*', '+', 0, '-', '.', 0, -/* 48 0 49 1 50 2 51 3 52 4 53 5 54 6 55 7 */ - '0', '1', '2', '3', '4', '5', '6', '7', -/* 56 8 57 9 58 : 59 ; 60 < 61 = 62 > 63 ? */ - '8', '9', 0, 0, 0, 0, 0, 0, -/* 64 @ 65 A 66 B 67 C 68 D 69 E 70 F 71 G */ - 0, 'a', 'b', 'c', 'd', 'e', 'f', 'g', -/* 72 H 73 I 74 J 75 K 76 L 77 M 78 N 79 O */ - 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', -/* 80 P 81 Q 82 R 83 S 84 T 85 U 86 V 87 W */ - 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', -/* 88 X 89 Y 90 Z 91 [ 92 \ 93 ] 94 ^ 95 _ */ - 'x', 'y', 'z', 0, 0, 0, '^', '_', -/* 96 ` 97 a 98 b 99 c 100 d 101 e 102 f 103 g */ - '`', 'a', 'b', 'c', 'd', 'e', 'f', 'g', -/* 104 h 105 i 106 j 107 k 108 l 109 m 110 n 111 o */ - 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', -/* 112 p 113 q 114 r 115 s 116 t 117 u 118 v 119 w */ - 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', -/* 120 x 121 y 122 z 123 { 124 | 125 } 126 ~ 127 del */ - 'x', 'y', 'z', 0, '|', 0, '~', 0 }; - - -static const int8_t unhex[256] = - {-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1 - ,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1 - ,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1 - , 0, 1, 2, 3, 4, 5, 6, 7, 8, 9,-1,-1,-1,-1,-1,-1 - ,-1,10,11,12,13,14,15,-1,-1,-1,-1,-1,-1,-1,-1,-1 - ,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1 - ,-1,10,11,12,13,14,15,-1,-1,-1,-1,-1,-1,-1,-1,-1 - ,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1 - }; - - #if HTTP_PARSER_STRICT # define T(v) 0 #else @@ -279,26 +86,8 @@ static const uint8_t normal_url_char[32] = { enum state { s_dead = 1 /* important that this is > 0 */ - , s_start_req_or_res - , s_res_or_resp_H - , s_start_res - , s_res_H - , s_res_HT - , s_res_HTT - , s_res_HTTP - , s_res_first_http_major - , s_res_http_major - , s_res_first_http_minor - , s_res_http_minor - , s_res_first_status_code - , s_res_status_code - , s_res_status_start - , s_res_status - , s_res_line_almost_done - , s_start_req - , s_req_method , s_req_spaces_before_url , s_req_schema , s_req_schema_slash @@ -311,83 +100,7 @@ enum state , s_req_query_string , s_req_fragment_start , s_req_fragment - , s_req_http_start - , s_req_http_H - , s_req_http_HT - , s_req_http_HTT - , s_req_http_HTTP - , s_req_first_http_major - , s_req_http_major - , s_req_first_http_minor - , s_req_http_minor - , s_req_line_almost_done - - , s_header_field_start - , s_header_field - , s_header_value_discard_ws - , s_header_value_discard_ws_almost_done - , s_header_value_discard_lws - , s_header_value_start - , s_header_value - , s_header_value_lws - - , s_header_almost_done - - , s_chunk_size_start - , s_chunk_size - , s_chunk_parameters - , s_chunk_size_almost_done - - , s_headers_almost_done , s_headers_done - - /* Important: 's_headers_done' must be the last 'header' state. All - * states beyond this must be 'body' states. It is used for overflow - * checking. See the PARSING_HEADER() macro. - */ - - , s_chunk_data - , s_chunk_data_almost_done - , s_chunk_data_done - - , s_body_identity - , s_body_identity_eof - - , s_message_done - }; - - -#define PARSING_HEADER(state) (state <= s_headers_done) - - -enum header_states - { h_general = 0 - , h_C - , h_CO - , h_CON - - , h_matching_connection - , h_matching_proxy_connection - , h_matching_content_length - , h_matching_transfer_encoding - , h_matching_upgrade - - , h_connection - , h_content_length - , h_transfer_encoding - , h_upgrade - - , h_matching_transfer_encoding_chunked - , h_matching_connection_token_start - , h_matching_connection_keep_alive - , h_matching_connection_close - , h_matching_connection_upgrade - , h_matching_connection_token - - , h_transfer_encoding_chunked - , h_connection_keep_alive - , h_connection_close - , h_connection_upgrade }; enum http_host_state @@ -407,8 +120,6 @@ enum http_host_state }; /* Macros for character classes; depends on strict-mode */ -#define CR '\r' -#define LF '\n' #define LOWER(c) (unsigned char)(c | 0x20) #define IS_ALPHA(c) (LOWER(c) >= 'a' && LOWER(c) <= 'z') #define IS_NUM(c) ((c) >= '0' && (c) <= '9') @@ -421,57 +132,16 @@ enum http_host_state (c) == ';' || (c) == ':' || (c) == '&' || (c) == '=' || (c) == '+' || \ (c) == '$' || (c) == ',') -#define STRICT_TOKEN(c) (tokens[(unsigned char)c]) - #if HTTP_PARSER_STRICT -#define TOKEN(c) (tokens[(unsigned char)c]) #define IS_URL_CHAR(c) (BIT_AT(normal_url_char, (unsigned char)c)) #define IS_HOST_CHAR(c) (IS_ALPHANUM(c) || (c) == '.' || (c) == '-') #else -#define TOKEN(c) ((c == ' ') ? ' ' : tokens[(unsigned char)c]) #define IS_URL_CHAR(c) \ (BIT_AT(normal_url_char, (unsigned char)c) || ((c) & 0x80)) #define IS_HOST_CHAR(c) \ (IS_ALPHANUM(c) || (c) == '.' || (c) == '-' || (c) == '_') #endif -/** - * Verify that a char is a valid visible (printable) US-ASCII - * character or %x80-FF - **/ -#define IS_HEADER_CHAR(ch) \ - (ch == CR || ch == LF || ch == 9 || ((unsigned char)ch > 31 && ch != 127)) - -#define start_state (parser->type == HTTP_REQUEST ? s_start_req : s_start_res) - - -#if HTTP_PARSER_STRICT -# define STRICT_CHECK(cond) \ -do { \ - if (cond) { \ - SET_ERRNO(HPE_STRICT); \ - goto error; \ - } \ -} while (0) -# define NEW_MESSAGE() (http_should_keep_alive(parser) ? start_state : s_dead) -#else -# define STRICT_CHECK(cond) -# define NEW_MESSAGE() start_state -#endif - - -/* Map errno values to strings for human-readable output */ -#define HTTP_STRERROR_GEN(n, s) { "HPE_" #n, s }, -static struct { - const char *name; - const char *description; -} http_strerror_tab[] = { - HTTP_ERRNO_MAP(HTTP_STRERROR_GEN) -}; -#undef HTTP_STRERROR_GEN - -int http_message_needs_eof(const http_parser *parser); - /* Our URL parser. * * This is designed to be shared by http_parser_execute() for URL validation, @@ -631,1545 +301,6 @@ parse_url_char(enum state s, const char ch) return s_dead; } -uint32_t http_parser_execute (http_parser *parser, - const http_parser_settings *settings, - const char *data, - uint32_t len) -{ - char c, ch; - int8_t unhex_val; - const char *p = data; - const char *header_field_mark = 0; - const char *header_value_mark = 0; - const char *url_mark = 0; - const char *body_mark = 0; - const char *status_mark = 0; - enum state p_state = (enum state) parser->state; - const unsigned int lenient = parser->lenient_http_headers; - - /* We're in an error state. Don't bother doing anything. */ - if (HTTP_PARSER_ERRNO(parser) != HPE_OK) { - return 0; - } - - if (len == 0) { - switch (CURRENT_STATE()) { - case s_body_identity_eof: - /* Use of CALLBACK_NOTIFY() here would erroneously return 1 byte read if - * we got paused. - */ - CALLBACK_NOTIFY_NOADVANCE(message_complete); - return 0; - - case s_dead: - case s_start_req_or_res: - case s_start_res: - case s_start_req: - return 0; - - default: - SET_ERRNO(HPE_INVALID_EOF_STATE); - return 1; - } - } - - - if (CURRENT_STATE() == s_header_field) - header_field_mark = data; - if (CURRENT_STATE() == s_header_value) - header_value_mark = data; - switch (CURRENT_STATE()) { - case s_req_path: - case s_req_schema: - case s_req_schema_slash: - case s_req_schema_slash_slash: - case s_req_server_start: - case s_req_server: - case s_req_server_with_at: - case s_req_query_string_start: - case s_req_query_string: - case s_req_fragment_start: - case s_req_fragment: - url_mark = data; - break; - case s_res_status: - status_mark = data; - break; - default: - break; - } - - for (p=data; p != data + len; p++) { - ch = *p; - - if (PARSING_HEADER(CURRENT_STATE())) - COUNT_HEADER_SIZE(1); - -reexecute: - switch (CURRENT_STATE()) { - - case s_dead: - /* this state is used after a 'Connection: close' message - * the parser will error out if it reads another message - */ - if (LIKELY(ch == CR || ch == LF)) - break; - - SET_ERRNO(HPE_CLOSED_CONNECTION); - goto error; - - case s_start_req_or_res: - { - if (ch == CR || ch == LF) - break; - parser->flags = 0; - parser->content_length = ULLONG_MAX; - - if (ch == 'H') { - UPDATE_STATE(s_res_or_resp_H); - - CALLBACK_NOTIFY(message_begin); - } else { - parser->type = HTTP_REQUEST; - UPDATE_STATE(s_start_req); - REEXECUTE(); - } - - break; - } - - case s_res_or_resp_H: - if (ch == 'T') { - parser->type = HTTP_RESPONSE; - UPDATE_STATE(s_res_HT); - } else { - if (UNLIKELY(ch != 'E')) { - SET_ERRNO(HPE_INVALID_CONSTANT); - goto error; - } - - parser->type = HTTP_REQUEST; - parser->method = HTTP_HEAD; - parser->index = 2; - UPDATE_STATE(s_req_method); - } - break; - - case s_start_res: - { - parser->flags = 0; - parser->content_length = ULLONG_MAX; - - switch (ch) { - case 'H': - UPDATE_STATE(s_res_H); - break; - - case CR: - case LF: - break; - - default: - SET_ERRNO(HPE_INVALID_CONSTANT); - goto error; - } - - CALLBACK_NOTIFY(message_begin); - break; - } - - case s_res_H: - STRICT_CHECK(ch != 'T'); - UPDATE_STATE(s_res_HT); - break; - - case s_res_HT: - STRICT_CHECK(ch != 'T'); - UPDATE_STATE(s_res_HTT); - break; - - case s_res_HTT: - STRICT_CHECK(ch != 'P'); - UPDATE_STATE(s_res_HTTP); - break; - - case s_res_HTTP: - STRICT_CHECK(ch != '/'); - UPDATE_STATE(s_res_first_http_major); - break; - - case s_res_first_http_major: - if (UNLIKELY(ch < '0' || ch > '9')) { - SET_ERRNO(HPE_INVALID_VERSION); - goto error; - } - - parser->http_major = ch - '0'; - UPDATE_STATE(s_res_http_major); - break; - - /* major HTTP version or dot */ - case s_res_http_major: - { - if (ch == '.') { - UPDATE_STATE(s_res_first_http_minor); - break; - } - - if (!IS_NUM(ch)) { - SET_ERRNO(HPE_INVALID_VERSION); - goto error; - } - - parser->http_major *= 10; - parser->http_major += ch - '0'; - - if (UNLIKELY(parser->http_major > 999)) { - SET_ERRNO(HPE_INVALID_VERSION); - goto error; - } - - break; - } - - /* first digit of minor HTTP version */ - case s_res_first_http_minor: - if (UNLIKELY(!IS_NUM(ch))) { - SET_ERRNO(HPE_INVALID_VERSION); - goto error; - } - - parser->http_minor = ch - '0'; - UPDATE_STATE(s_res_http_minor); - break; - - /* minor HTTP version or end of request line */ - case s_res_http_minor: - { - if (ch == ' ') { - UPDATE_STATE(s_res_first_status_code); - break; - } - - if (UNLIKELY(!IS_NUM(ch))) { - SET_ERRNO(HPE_INVALID_VERSION); - goto error; - } - - parser->http_minor *= 10; - parser->http_minor += ch - '0'; - - if (UNLIKELY(parser->http_minor > 999)) { - SET_ERRNO(HPE_INVALID_VERSION); - goto error; - } - - break; - } - - case s_res_first_status_code: - { - if (!IS_NUM(ch)) { - if (ch == ' ') { - break; - } - - SET_ERRNO(HPE_INVALID_STATUS); - goto error; - } - parser->status_code = ch - '0'; - UPDATE_STATE(s_res_status_code); - break; - } - - case s_res_status_code: - { - if (!IS_NUM(ch)) { - switch (ch) { - case ' ': - UPDATE_STATE(s_res_status_start); - break; - case CR: - UPDATE_STATE(s_res_line_almost_done); - break; - case LF: - UPDATE_STATE(s_header_field_start); - break; - default: - SET_ERRNO(HPE_INVALID_STATUS); - goto error; - } - break; - } - - parser->status_code *= 10; - parser->status_code += ch - '0'; - - if (UNLIKELY(parser->status_code > 999)) { - SET_ERRNO(HPE_INVALID_STATUS); - goto error; - } - - break; - } - - case s_res_status_start: - { - if (ch == CR) { - UPDATE_STATE(s_res_line_almost_done); - break; - } - - if (ch == LF) { - UPDATE_STATE(s_header_field_start); - break; - } - - MARK(status); - UPDATE_STATE(s_res_status); - parser->index = 0; - break; - } - - case s_res_status: - if (ch == CR) { - UPDATE_STATE(s_res_line_almost_done); - CALLBACK_DATA(status); - break; - } - - if (ch == LF) { - UPDATE_STATE(s_header_field_start); - CALLBACK_DATA(status); - break; - } - - break; - - case s_res_line_almost_done: - STRICT_CHECK(ch != LF); - UPDATE_STATE(s_header_field_start); - break; - - case s_start_req: - { - if (ch == CR || ch == LF) - break; - parser->flags = 0; - parser->content_length = ULLONG_MAX; - - if (UNLIKELY(!IS_ALPHA(ch))) { - SET_ERRNO(HPE_INVALID_METHOD); - goto error; - } - - parser->method = (enum http_method) 0; - parser->index = 1; - switch (ch) { - case 'A': parser->method = HTTP_ACL; break; - case 'B': parser->method = HTTP_BIND; break; - case 'C': parser->method = HTTP_CONNECT; /* or COPY, CHECKOUT */ break; - case 'D': parser->method = HTTP_DELETE; break; - case 'G': parser->method = HTTP_GET; break; - case 'H': parser->method = HTTP_HEAD; break; - case 'L': parser->method = HTTP_LOCK; /* or LINK */ break; - case 'M': parser->method = HTTP_MKCOL; /* or MOVE, MKACTIVITY, MERGE, M-SEARCH, MKCALENDAR */ break; - case 'N': parser->method = HTTP_NOTIFY; break; - case 'O': parser->method = HTTP_OPTIONS; break; - case 'P': parser->method = HTTP_POST; - /* or PROPFIND|PROPPATCH|PUT|PATCH|PURGE */ - break; - case 'R': parser->method = HTTP_REPORT; /* or REBIND */ break; - case 'S': parser->method = HTTP_SUBSCRIBE; /* or SEARCH */ break; - case 'T': parser->method = HTTP_TRACE; break; - case 'U': parser->method = HTTP_UNLOCK; /* or UNSUBSCRIBE, UNBIND, UNLINK */ break; - default: - SET_ERRNO(HPE_INVALID_METHOD); - goto error; - } - UPDATE_STATE(s_req_method); - - CALLBACK_NOTIFY(message_begin); - - break; - } - - case s_req_method: - { - const char *matcher; - if (UNLIKELY(ch == '\0')) { - SET_ERRNO(HPE_INVALID_METHOD); - goto error; - } - - matcher = method_strings[parser->method]; - if (ch == ' ' && matcher[parser->index] == '\0') { - UPDATE_STATE(s_req_spaces_before_url); - } else if (ch == matcher[parser->index]) { - ; /* nada */ - } else if (IS_ALPHA(ch)) { - - switch (parser->method << 16 | parser->index << 8 | ch) { -#define XX(meth, pos, ch, new_meth) \ - case (HTTP_##meth << 16 | pos << 8 | ch): \ - parser->method = HTTP_##new_meth; break; - - XX(POST, 1, 'U', PUT) - XX(POST, 1, 'A', PATCH) - XX(CONNECT, 1, 'H', CHECKOUT) - XX(CONNECT, 2, 'P', COPY) - XX(MKCOL, 1, 'O', MOVE) - XX(MKCOL, 1, 'E', MERGE) - XX(MKCOL, 2, 'A', MKACTIVITY) - XX(MKCOL, 3, 'A', MKCALENDAR) - XX(SUBSCRIBE, 1, 'E', SEARCH) - XX(REPORT, 2, 'B', REBIND) - XX(POST, 1, 'R', PROPFIND) - XX(PROPFIND, 4, 'P', PROPPATCH) - XX(PUT, 2, 'R', PURGE) - XX(LOCK, 1, 'I', LINK) - XX(UNLOCK, 2, 'S', UNSUBSCRIBE) - XX(UNLOCK, 2, 'B', UNBIND) - XX(UNLOCK, 3, 'I', UNLINK) -#undef XX - - default: - SET_ERRNO(HPE_INVALID_METHOD); - goto error; - } - } else if (ch == '-' && - parser->index == 1 && - parser->method == HTTP_MKCOL) { - parser->method = HTTP_MSEARCH; - } else { - SET_ERRNO(HPE_INVALID_METHOD); - goto error; - } - - ++parser->index; - break; - } - - case s_req_spaces_before_url: - { - if (ch == ' ') break; - - MARK(url); - if (parser->method == HTTP_CONNECT) { - UPDATE_STATE(s_req_server_start); - } - - UPDATE_STATE(parse_url_char(CURRENT_STATE(), ch)); - if (UNLIKELY(CURRENT_STATE() == s_dead)) { - SET_ERRNO(HPE_INVALID_URL); - goto error; - } - - break; - } - - case s_req_schema: - case s_req_schema_slash: - case s_req_schema_slash_slash: - case s_req_server_start: - { - switch (ch) { - /* No whitespace allowed here */ - case ' ': - case CR: - case LF: - SET_ERRNO(HPE_INVALID_URL); - goto error; - default: - UPDATE_STATE(parse_url_char(CURRENT_STATE(), ch)); - if (UNLIKELY(CURRENT_STATE() == s_dead)) { - SET_ERRNO(HPE_INVALID_URL); - goto error; - } - } - - break; - } - - case s_req_server: - case s_req_server_with_at: - case s_req_path: - case s_req_query_string_start: - case s_req_query_string: - case s_req_fragment_start: - case s_req_fragment: - { - switch (ch) { - case ' ': - UPDATE_STATE(s_req_http_start); - CALLBACK_DATA(url); - break; - case CR: - case LF: - parser->http_major = 0; - parser->http_minor = 9; - UPDATE_STATE((ch == CR) ? - s_req_line_almost_done : - s_header_field_start); - CALLBACK_DATA(url); - break; - default: - UPDATE_STATE(parse_url_char(CURRENT_STATE(), ch)); - if (UNLIKELY(CURRENT_STATE() == s_dead)) { - SET_ERRNO(HPE_INVALID_URL); - goto error; - } - } - break; - } - - case s_req_http_start: - switch (ch) { - case 'H': - UPDATE_STATE(s_req_http_H); - break; - case ' ': - break; - default: - SET_ERRNO(HPE_INVALID_CONSTANT); - goto error; - } - break; - - case s_req_http_H: - STRICT_CHECK(ch != 'T'); - UPDATE_STATE(s_req_http_HT); - break; - - case s_req_http_HT: - STRICT_CHECK(ch != 'T'); - UPDATE_STATE(s_req_http_HTT); - break; - - case s_req_http_HTT: - STRICT_CHECK(ch != 'P'); - UPDATE_STATE(s_req_http_HTTP); - break; - - case s_req_http_HTTP: - STRICT_CHECK(ch != '/'); - UPDATE_STATE(s_req_first_http_major); - break; - - /* first digit of major HTTP version */ - case s_req_first_http_major: - if (UNLIKELY(ch < '1' || ch > '9')) { - SET_ERRNO(HPE_INVALID_VERSION); - goto error; - } - - parser->http_major = ch - '0'; - UPDATE_STATE(s_req_http_major); - break; - - /* major HTTP version or dot */ - case s_req_http_major: - { - if (ch == '.') { - UPDATE_STATE(s_req_first_http_minor); - break; - } - - if (UNLIKELY(!IS_NUM(ch))) { - SET_ERRNO(HPE_INVALID_VERSION); - goto error; - } - - parser->http_major *= 10; - parser->http_major += ch - '0'; - - if (UNLIKELY(parser->http_major > 999)) { - SET_ERRNO(HPE_INVALID_VERSION); - goto error; - } - - break; - } - - /* first digit of minor HTTP version */ - case s_req_first_http_minor: - if (UNLIKELY(!IS_NUM(ch))) { - SET_ERRNO(HPE_INVALID_VERSION); - goto error; - } - - parser->http_minor = ch - '0'; - UPDATE_STATE(s_req_http_minor); - break; - - /* minor HTTP version or end of request line */ - case s_req_http_minor: - { - if (ch == CR) { - UPDATE_STATE(s_req_line_almost_done); - break; - } - - if (ch == LF) { - UPDATE_STATE(s_header_field_start); - break; - } - - /* XXX allow spaces after digit? */ - - if (UNLIKELY(!IS_NUM(ch))) { - SET_ERRNO(HPE_INVALID_VERSION); - goto error; - } - - parser->http_minor *= 10; - parser->http_minor += ch - '0'; - - if (UNLIKELY(parser->http_minor > 999)) { - SET_ERRNO(HPE_INVALID_VERSION); - goto error; - } - - break; - } - - /* end of request line */ - case s_req_line_almost_done: - { - if (UNLIKELY(ch != LF)) { - SET_ERRNO(HPE_LF_EXPECTED); - goto error; - } - - UPDATE_STATE(s_header_field_start); - break; - } - - case s_header_field_start: - { - if (ch == CR) { - UPDATE_STATE(s_headers_almost_done); - break; - } - - if (ch == LF) { - /* they might be just sending \n instead of \r\n so this would be - * the second \n to denote the end of headers*/ - UPDATE_STATE(s_headers_almost_done); - REEXECUTE(); - } - - c = TOKEN(ch); - - if (UNLIKELY(!c)) { - SET_ERRNO(HPE_INVALID_HEADER_TOKEN); - goto error; - } - - MARK(header_field); - - parser->index = 0; - UPDATE_STATE(s_header_field); - - switch (c) { - case 'c': - parser->header_state = h_C; - break; - - case 'p': - parser->header_state = h_matching_proxy_connection; - break; - - case 't': - parser->header_state = h_matching_transfer_encoding; - break; - - case 'u': - parser->header_state = h_matching_upgrade; - break; - - default: - parser->header_state = h_general; - break; - } - break; - } - - case s_header_field: - { - const char* start = p; - for (; p != data + len; p++) { - ch = *p; - c = TOKEN(ch); - - if (!c) - break; - - switch (parser->header_state) { - case h_general: - break; - - case h_C: - parser->index++; - parser->header_state = (c == 'o' ? h_CO : h_general); - break; - - case h_CO: - parser->index++; - parser->header_state = (c == 'n' ? h_CON : h_general); - break; - - case h_CON: - parser->index++; - switch (c) { - case 'n': - parser->header_state = h_matching_connection; - break; - case 't': - parser->header_state = h_matching_content_length; - break; - default: - parser->header_state = h_general; - break; - } - break; - - /* connection */ - - case h_matching_connection: - parser->index++; - if (parser->index > sizeof(CONNECTION)-1 - || c != CONNECTION[parser->index]) { - parser->header_state = h_general; - } else if (parser->index == sizeof(CONNECTION)-2) { - parser->header_state = h_connection; - } - break; - - /* proxy-connection */ - - case h_matching_proxy_connection: - parser->index++; - if (parser->index > sizeof(PROXY_CONNECTION)-1 - || c != PROXY_CONNECTION[parser->index]) { - parser->header_state = h_general; - } else if (parser->index == sizeof(PROXY_CONNECTION)-2) { - parser->header_state = h_connection; - } - break; - - /* content-length */ - - case h_matching_content_length: - parser->index++; - if (parser->index > sizeof(CONTENT_LENGTH)-1 - || c != CONTENT_LENGTH[parser->index]) { - parser->header_state = h_general; - } else if (parser->index == sizeof(CONTENT_LENGTH)-2) { - parser->header_state = h_content_length; - } - break; - - /* transfer-encoding */ - - case h_matching_transfer_encoding: - parser->index++; - if (parser->index > sizeof(TRANSFER_ENCODING)-1 - || c != TRANSFER_ENCODING[parser->index]) { - parser->header_state = h_general; - } else if (parser->index == sizeof(TRANSFER_ENCODING)-2) { - parser->header_state = h_transfer_encoding; - } - break; - - /* upgrade */ - - case h_matching_upgrade: - parser->index++; - if (parser->index > sizeof(UPGRADE)-1 - || c != UPGRADE[parser->index]) { - parser->header_state = h_general; - } else if (parser->index == sizeof(UPGRADE)-2) { - parser->header_state = h_upgrade; - } - break; - - case h_connection: - case h_content_length: - case h_transfer_encoding: - case h_upgrade: - if (ch != ' ') parser->header_state = h_general; - break; - - default: - assert(0 && "Unknown header_state"); - break; - } - } - - COUNT_HEADER_SIZE(p - start); - - if (p == data + len) { - --p; - break; - } - - if (ch == ':') { - UPDATE_STATE(s_header_value_discard_ws); - CALLBACK_DATA(header_field); - break; - } - - SET_ERRNO(HPE_INVALID_HEADER_TOKEN); - goto error; - } - - case s_header_value_discard_ws: - if (ch == ' ' || ch == '\t') break; - - if (ch == CR) { - UPDATE_STATE(s_header_value_discard_ws_almost_done); - break; - } - - if (ch == LF) { - UPDATE_STATE(s_header_value_discard_lws); - break; - } - - /* FALLTHROUGH */ - - case s_header_value_start: - { - MARK(header_value); - - UPDATE_STATE(s_header_value); - parser->index = 0; - - c = LOWER(ch); - - switch (parser->header_state) { - case h_upgrade: - parser->flags |= F_UPGRADE; - parser->header_state = h_general; - break; - - case h_transfer_encoding: - /* looking for 'Transfer-Encoding: chunked' */ - if ('c' == c) { - parser->header_state = h_matching_transfer_encoding_chunked; - } else { - parser->header_state = h_general; - } - break; - - case h_content_length: - if (UNLIKELY(!IS_NUM(ch))) { - SET_ERRNO(HPE_INVALID_CONTENT_LENGTH); - goto error; - } - - if (parser->flags & F_CONTENTLENGTH) { - SET_ERRNO(HPE_UNEXPECTED_CONTENT_LENGTH); - goto error; - } - - parser->flags |= F_CONTENTLENGTH; - parser->content_length = ch - '0'; - break; - - case h_connection: - /* looking for 'Connection: keep-alive' */ - if (c == 'k') { - parser->header_state = h_matching_connection_keep_alive; - /* looking for 'Connection: close' */ - } else if (c == 'c') { - parser->header_state = h_matching_connection_close; - } else if (c == 'u') { - parser->header_state = h_matching_connection_upgrade; - } else { - parser->header_state = h_matching_connection_token; - } - break; - - /* Multi-value `Connection` header */ - case h_matching_connection_token_start: - break; - - default: - parser->header_state = h_general; - break; - } - break; - } - - case s_header_value: - { - const char* start = p; - enum header_states h_state = (enum header_states) parser->header_state; - for (; p != data + len; p++) { - ch = *p; - if (ch == CR) { - UPDATE_STATE(s_header_almost_done); - parser->header_state = h_state; - CALLBACK_DATA(header_value); - break; - } - - if (ch == LF) { - UPDATE_STATE(s_header_almost_done); - COUNT_HEADER_SIZE(p - start); - parser->header_state = h_state; - CALLBACK_DATA_NOADVANCE(header_value); - REEXECUTE(); - } - - if (!lenient && !IS_HEADER_CHAR(ch)) { - SET_ERRNO(HPE_INVALID_HEADER_TOKEN); - goto error; - } - - c = LOWER(ch); - - switch (h_state) { - case h_general: - { - const char* p_cr; - const char* p_lf; - uint32_t limit = data + len - p; - - limit = MIN(limit, HTTP_MAX_HEADER_SIZE); - - p_cr = (const char*) memchr(p, CR, limit); - p_lf = (const char*) memchr(p, LF, limit); - if (p_cr != NULL) { - if (p_lf != NULL && p_cr >= p_lf) - p = p_lf; - else - p = p_cr; - } else if (UNLIKELY(p_lf != NULL)) { - p = p_lf; - } else { - p = data + len; - } - --p; - - break; - } - - case h_connection: - case h_transfer_encoding: - assert(0 && "Shouldn't get here."); - break; - - case h_content_length: - { - uint64_t t; - - if (ch == ' ') break; - - if (UNLIKELY(!IS_NUM(ch))) { - SET_ERRNO(HPE_INVALID_CONTENT_LENGTH); - parser->header_state = h_state; - goto error; - } - - t = parser->content_length; - t *= 10; - t += ch - '0'; - - /* Overflow? Test against a conservative limit for simplicity. */ - if (UNLIKELY((ULLONG_MAX - 10) / 10 < parser->content_length)) { - SET_ERRNO(HPE_INVALID_CONTENT_LENGTH); - parser->header_state = h_state; - goto error; - } - - parser->content_length = t; - break; - } - - /* Transfer-Encoding: chunked */ - case h_matching_transfer_encoding_chunked: - parser->index++; - if (parser->index > sizeof(CHUNKED)-1 - || c != CHUNKED[parser->index]) { - h_state = h_general; - } else if (parser->index == sizeof(CHUNKED)-2) { - h_state = h_transfer_encoding_chunked; - } - break; - - case h_matching_connection_token_start: - /* looking for 'Connection: keep-alive' */ - if (c == 'k') { - h_state = h_matching_connection_keep_alive; - /* looking for 'Connection: close' */ - } else if (c == 'c') { - h_state = h_matching_connection_close; - } else if (c == 'u') { - h_state = h_matching_connection_upgrade; - } else if (STRICT_TOKEN(c)) { - h_state = h_matching_connection_token; - } else if (c == ' ' || c == '\t') { - /* Skip lws */ - } else { - h_state = h_general; - } - break; - - /* looking for 'Connection: keep-alive' */ - case h_matching_connection_keep_alive: - parser->index++; - if (parser->index > sizeof(KEEP_ALIVE)-1 - || c != KEEP_ALIVE[parser->index]) { - h_state = h_matching_connection_token; - } else if (parser->index == sizeof(KEEP_ALIVE)-2) { - h_state = h_connection_keep_alive; - } - break; - - /* looking for 'Connection: close' */ - case h_matching_connection_close: - parser->index++; - if (parser->index > sizeof(CLOSE)-1 || c != CLOSE[parser->index]) { - h_state = h_matching_connection_token; - } else if (parser->index == sizeof(CLOSE)-2) { - h_state = h_connection_close; - } - break; - - /* looking for 'Connection: upgrade' */ - case h_matching_connection_upgrade: - parser->index++; - if (parser->index > sizeof(UPGRADE) - 1 || - c != UPGRADE[parser->index]) { - h_state = h_matching_connection_token; - } else if (parser->index == sizeof(UPGRADE)-2) { - h_state = h_connection_upgrade; - } - break; - - case h_matching_connection_token: - if (ch == ',') { - h_state = h_matching_connection_token_start; - parser->index = 0; - } - break; - - case h_transfer_encoding_chunked: - if (ch != ' ') h_state = h_general; - break; - - case h_connection_keep_alive: - case h_connection_close: - case h_connection_upgrade: - if (ch == ',') { - if (h_state == h_connection_keep_alive) { - parser->flags |= F_CONNECTION_KEEP_ALIVE; - } else if (h_state == h_connection_close) { - parser->flags |= F_CONNECTION_CLOSE; - } else if (h_state == h_connection_upgrade) { - parser->flags |= F_CONNECTION_UPGRADE; - } - h_state = h_matching_connection_token_start; - parser->index = 0; - } else if (ch != ' ') { - h_state = h_matching_connection_token; - } - break; - - default: - UPDATE_STATE(s_header_value); - h_state = h_general; - break; - } - } - parser->header_state = h_state; - - COUNT_HEADER_SIZE(p - start); - - if (p == data + len) - --p; - break; - } - - case s_header_almost_done: - { - if (UNLIKELY(ch != LF)) { - SET_ERRNO(HPE_LF_EXPECTED); - goto error; - } - - UPDATE_STATE(s_header_value_lws); - break; - } - - case s_header_value_lws: - { - if (ch == ' ' || ch == '\t') { - UPDATE_STATE(s_header_value_start); - REEXECUTE(); - } - - /* finished the header */ - switch (parser->header_state) { - case h_connection_keep_alive: - parser->flags |= F_CONNECTION_KEEP_ALIVE; - break; - case h_connection_close: - parser->flags |= F_CONNECTION_CLOSE; - break; - case h_transfer_encoding_chunked: - parser->flags |= F_CHUNKED; - break; - case h_connection_upgrade: - parser->flags |= F_CONNECTION_UPGRADE; - break; - default: - break; - } - - UPDATE_STATE(s_header_field_start); - REEXECUTE(); - } - - case s_header_value_discard_ws_almost_done: - { - STRICT_CHECK(ch != LF); - UPDATE_STATE(s_header_value_discard_lws); - break; - } - - case s_header_value_discard_lws: - { - if (ch == ' ' || ch == '\t') { - UPDATE_STATE(s_header_value_discard_ws); - break; - } else { - switch (parser->header_state) { - case h_connection_keep_alive: - parser->flags |= F_CONNECTION_KEEP_ALIVE; - break; - case h_connection_close: - parser->flags |= F_CONNECTION_CLOSE; - break; - case h_connection_upgrade: - parser->flags |= F_CONNECTION_UPGRADE; - break; - case h_transfer_encoding_chunked: - parser->flags |= F_CHUNKED; - break; - default: - break; - } - - /* header value was empty */ - MARK(header_value); - UPDATE_STATE(s_header_field_start); - CALLBACK_DATA_NOADVANCE(header_value); - REEXECUTE(); - } - } - - case s_headers_almost_done: - { - STRICT_CHECK(ch != LF); - - if (parser->flags & F_TRAILING) { - /* End of a chunked request */ - UPDATE_STATE(s_message_done); - CALLBACK_NOTIFY_NOADVANCE(chunk_complete); - REEXECUTE(); - } - - /* Cannot use chunked encoding and a content-length header together - per the HTTP specification. */ - if ((parser->flags & F_CHUNKED) && - (parser->flags & F_CONTENTLENGTH)) { - SET_ERRNO(HPE_UNEXPECTED_CONTENT_LENGTH); - goto error; - } - - UPDATE_STATE(s_headers_done); - - /* Set this here so that on_headers_complete() callbacks can see it */ - parser->upgrade = - ((parser->flags & (F_UPGRADE | F_CONNECTION_UPGRADE)) == - (F_UPGRADE | F_CONNECTION_UPGRADE) || - parser->method == HTTP_CONNECT); - - /* Here we call the headers_complete callback. This is somewhat - * different than other callbacks because if the user returns 1, we - * will interpret that as saying that this message has no body. This - * is needed for the annoying case of recieving a response to a HEAD - * request. - * - * We'd like to use CALLBACK_NOTIFY_NOADVANCE() here but we cannot, so - * we have to simulate it by handling a change in errno below. - */ - if (settings->on_headers_complete) { - switch (settings->on_headers_complete(parser)) { - case 0: - break; - - case 2: - parser->upgrade = 1; - - case 1: - parser->flags |= F_SKIPBODY; - break; - - default: - SET_ERRNO(HPE_CB_headers_complete); - RETURN(p - data); /* Error */ - } - } - - if (HTTP_PARSER_ERRNO(parser) != HPE_OK) { - RETURN(p - data); - } - - REEXECUTE(); - } - - case s_headers_done: - { - int hasBody; - STRICT_CHECK(ch != LF); - - parser->nread = 0; - - hasBody = parser->flags & F_CHUNKED || - (parser->content_length > 0 && parser->content_length != ULLONG_MAX); - if (parser->upgrade && (parser->method == HTTP_CONNECT || - (parser->flags & F_SKIPBODY) || !hasBody)) { - /* Exit, the rest of the message is in a different protocol. */ - UPDATE_STATE(NEW_MESSAGE()); - CALLBACK_NOTIFY(message_complete); - RETURN((p - data) + 1); - } - - if (parser->flags & F_SKIPBODY) { - UPDATE_STATE(NEW_MESSAGE()); - CALLBACK_NOTIFY(message_complete); - } else if (parser->flags & F_CHUNKED) { - /* chunked encoding - ignore Content-Length header */ - UPDATE_STATE(s_chunk_size_start); - } else { - if (parser->content_length == 0) { - /* Content-Length header given but zero: Content-Length: 0\r\n */ - UPDATE_STATE(NEW_MESSAGE()); - CALLBACK_NOTIFY(message_complete); - } else if (parser->content_length != ULLONG_MAX) { - /* Content-Length header given and non-zero */ - UPDATE_STATE(s_body_identity); - } else { - if (!http_message_needs_eof(parser)) { - /* Assume content-length 0 - read the next */ - UPDATE_STATE(NEW_MESSAGE()); - CALLBACK_NOTIFY(message_complete); - } else { - /* Read body until EOF */ - UPDATE_STATE(s_body_identity_eof); - } - } - } - - break; - } - - case s_body_identity: - { - uint64_t to_read = MIN(parser->content_length, - (uint64_t) ((data + len) - p)); - - assert(parser->content_length != 0 - && parser->content_length != ULLONG_MAX); - - /* The difference between advancing content_length and p is because - * the latter will automaticaly advance on the next loop iteration. - * Further, if content_length ends up at 0, we want to see the last - * byte again for our message complete callback. - */ - MARK(body); - parser->content_length -= to_read; - p += to_read - 1; - - if (parser->content_length == 0) { - UPDATE_STATE(s_message_done); - - /* Mimic CALLBACK_DATA_NOADVANCE() but with one extra byte. - * - * The alternative to doing this is to wait for the next byte to - * trigger the data callback, just as in every other case. The - * problem with this is that this makes it difficult for the test - * harness to distinguish between complete-on-EOF and - * complete-on-length. It's not clear that this distinction is - * important for applications, but let's keep it for now. - */ - CALLBACK_DATA_(body, p - body_mark + 1, p - data); - REEXECUTE(); - } - - break; - } - - /* read until EOF */ - case s_body_identity_eof: - MARK(body); - p = data + len - 1; - - break; - - case s_message_done: - UPDATE_STATE(NEW_MESSAGE()); - CALLBACK_NOTIFY(message_complete); - if (parser->upgrade) { - /* Exit, the rest of the message is in a different protocol. */ - RETURN((p - data) + 1); - } - break; - - case s_chunk_size_start: - { - assert(parser->nread == 1); - assert(parser->flags & F_CHUNKED); - - unhex_val = unhex[(unsigned char)ch]; - if (UNLIKELY(unhex_val == -1)) { - SET_ERRNO(HPE_INVALID_CHUNK_SIZE); - goto error; - } - - parser->content_length = unhex_val; - UPDATE_STATE(s_chunk_size); - break; - } - - case s_chunk_size: - { - uint64_t t; - - assert(parser->flags & F_CHUNKED); - - if (ch == CR) { - UPDATE_STATE(s_chunk_size_almost_done); - break; - } - - unhex_val = unhex[(unsigned char)ch]; - - if (unhex_val == -1) { - if (ch == ';' || ch == ' ') { - UPDATE_STATE(s_chunk_parameters); - break; - } - - SET_ERRNO(HPE_INVALID_CHUNK_SIZE); - goto error; - } - - t = parser->content_length; - t *= 16; - t += unhex_val; - - /* Overflow? Test against a conservative limit for simplicity. */ - if (UNLIKELY((ULLONG_MAX - 16) / 16 < parser->content_length)) { - SET_ERRNO(HPE_INVALID_CONTENT_LENGTH); - goto error; - } - - parser->content_length = t; - break; - } - - case s_chunk_parameters: - { - assert(parser->flags & F_CHUNKED); - /* just ignore this shit. TODO check for overflow */ - if (ch == CR) { - UPDATE_STATE(s_chunk_size_almost_done); - break; - } - break; - } - - case s_chunk_size_almost_done: - { - assert(parser->flags & F_CHUNKED); - STRICT_CHECK(ch != LF); - - parser->nread = 0; - - if (parser->content_length == 0) { - parser->flags |= F_TRAILING; - UPDATE_STATE(s_header_field_start); - } else { - UPDATE_STATE(s_chunk_data); - } - CALLBACK_NOTIFY(chunk_header); - break; - } - - case s_chunk_data: - { - uint64_t to_read = MIN(parser->content_length, - (uint64_t) ((data + len) - p)); - - assert(parser->flags & F_CHUNKED); - assert(parser->content_length != 0 - && parser->content_length != ULLONG_MAX); - - /* See the explanation in s_body_identity for why the content - * length and data pointers are managed this way. - */ - MARK(body); - parser->content_length -= to_read; - p += to_read - 1; - - if (parser->content_length == 0) { - UPDATE_STATE(s_chunk_data_almost_done); - } - - break; - } - - case s_chunk_data_almost_done: - assert(parser->flags & F_CHUNKED); - assert(parser->content_length == 0); - STRICT_CHECK(ch != CR); - UPDATE_STATE(s_chunk_data_done); - CALLBACK_DATA(body); - break; - - case s_chunk_data_done: - assert(parser->flags & F_CHUNKED); - STRICT_CHECK(ch != LF); - parser->nread = 0; - UPDATE_STATE(s_chunk_size_start); - CALLBACK_NOTIFY(chunk_complete); - break; - - default: - assert(0 && "unhandled state"); - SET_ERRNO(HPE_INVALID_INTERNAL_STATE); - goto error; - } - } - - /* Run callbacks for any marks that we have leftover after we ran our of - * bytes. There should be at most one of these set, so it's OK to invoke - * them in series (unset marks will not result in callbacks). - * - * We use the NOADVANCE() variety of callbacks here because 'p' has already - * overflowed 'data' and this allows us to correct for the off-by-one that - * we'd otherwise have (since CALLBACK_DATA() is meant to be run with a 'p' - * value that's in-bounds). - */ - - assert(((header_field_mark ? 1 : 0) + - (header_value_mark ? 1 : 0) + - (url_mark ? 1 : 0) + - (body_mark ? 1 : 0) + - (status_mark ? 1 : 0)) <= 1); - - CALLBACK_DATA_NOADVANCE(header_field); - CALLBACK_DATA_NOADVANCE(header_value); - CALLBACK_DATA_NOADVANCE(url); - CALLBACK_DATA_NOADVANCE(body); - CALLBACK_DATA_NOADVANCE(status); - - RETURN(len); - -error: - if (HTTP_PARSER_ERRNO(parser) == HPE_OK) { - SET_ERRNO(HPE_UNKNOWN); - } - - RETURN(p - data); -} - - -/* Does the parser need to see an EOF to find the end of the message? */ -int -http_message_needs_eof (const http_parser *parser) -{ - if (parser->type == HTTP_REQUEST) { - return 0; - } - - /* See RFC 2616 section 4.4 */ - if (parser->status_code / 100 == 1 || /* 1xx e.g. Continue */ - parser->status_code == 204 || /* No Content */ - parser->status_code == 304 || /* Not Modified */ - parser->flags & F_SKIPBODY) { /* response to a HEAD request */ - return 0; - } - - if ((parser->flags & F_CHUNKED) || parser->content_length != ULLONG_MAX) { - return 0; - } - - return 1; -} - - -int -http_should_keep_alive (const http_parser *parser) -{ - if (parser->http_major > 0 && parser->http_minor > 0) { - /* HTTP/1.1 */ - if (parser->flags & F_CONNECTION_CLOSE) { - return 0; - } - } else { - /* HTTP/1.0 or earlier */ - if (!(parser->flags & F_CONNECTION_KEEP_ALIVE)) { - return 0; - } - } - - return !http_message_needs_eof(parser); -} - - -const char * -http_method_str (enum http_method m) -{ - return ELEM_AT(method_strings, m, ""); -} - - -void -http_parser_init (http_parser *parser, enum http_parser_type t) -{ - void *data = parser->data; /* preserve application data */ - memset(parser, 0, sizeof(*parser)); - parser->data = data; - parser->type = t; - parser->state = (t == HTTP_REQUEST ? s_start_req : (t == HTTP_RESPONSE ? s_start_res : s_start_req_or_res)); - parser->http_errno = HPE_OK; -} - -void -http_parser_settings_init(http_parser_settings *settings) -{ - memset(settings, 0, sizeof(*settings)); -} - -const char * -http_errno_name(enum http_errno err) { - assert(((uint32_t) err) < ARRAY_SIZE(http_strerror_tab)); - return http_strerror_tab[err].name; -} - -const char * -http_errno_description(enum http_errno err) { - assert(((uint32_t) err) < ARRAY_SIZE(http_strerror_tab)); - return http_strerror_tab[err].description; -} - static enum http_host_state http_parse_host_char(enum http_host_state s, const char ch) { switch(s) { @@ -2443,25 +574,6 @@ http_parser_parse_url(const char *buf, uint32_t buflen, int is_connect, return 0; } -void -http_parser_pause(http_parser *parser, int paused) { - /* Users should only be pausing/unpausing a parser that is not in an error - * state. In non-debug builds, there's not much that we can do about this - * other than ignore it. - */ - if (HTTP_PARSER_ERRNO(parser) == HPE_OK || - HTTP_PARSER_ERRNO(parser) == HPE_PAUSED) { - SET_ERRNO((paused) ? HPE_PAUSED : HPE_OK); - } else { - assert(0 && "Attempting to pause parser in error state"); - } -} - -int -http_body_is_final(const struct http_parser *parser) { - return parser->state == s_message_done; -} - unsigned long http_parser_version(void) { return HTTP_PARSER_VERSION_MAJOR * 0x10000 | diff --git a/src/utility/http_parser.h b/src/utility/http_parser.h index 472bf54..85a5238 100644 --- a/src/utility/http_parser.h +++ b/src/utility/http_parser.h @@ -30,21 +30,7 @@ extern "C" { #define HTTP_PARSER_VERSION_MINOR 7 #define HTTP_PARSER_VERSION_PATCH 1 -#if defined(_WIN32) && !defined(__MINGW32__) && \ - (!defined(_MSC_VER) || _MSC_VER<1600) && !defined(__WINE__) -#include -#include -typedef __int8 int8_t; -typedef unsigned __int8 uint8_t; -typedef __int16 int16_t; -typedef unsigned __int16 uint16_t; -typedef __int32 int32_t; -typedef unsigned __int32 uint32_t; -typedef __int64 int64_t; -typedef unsigned __int64 uint64_t; -#else #include -#endif /* Compile with -DHTTP_PARSER_STRICT=0 to make less checks, but run * faster @@ -53,289 +39,6 @@ typedef unsigned __int64 uint64_t; # define HTTP_PARSER_STRICT 1 #endif -/* Maximium header size allowed. If the macro is not defined - * before including this header then the default is used. To - * change the maximum header size, define the macro in the build - * environment (e.g. -DHTTP_MAX_HEADER_SIZE=). To remove - * the effective limit on the size of the header, define the macro - * to a very large number (e.g. -DHTTP_MAX_HEADER_SIZE=0x7fffffff) - */ -#ifndef HTTP_MAX_HEADER_SIZE -# define HTTP_MAX_HEADER_SIZE (80*1024) -#endif - -typedef struct http_parser http_parser; -typedef struct http_parser_settings http_parser_settings; - - -/* Callbacks should return non-zero to indicate an error. The parser will - * then halt execution. - * - * The one exception is on_headers_complete. In a HTTP_RESPONSE parser - * returning '1' from on_headers_complete will tell the parser that it - * should not expect a body. This is used when receiving a response to a - * HEAD request which may contain 'Content-Length' or 'Transfer-Encoding: - * chunked' headers that indicate the presence of a body. - * - * Returning `2` from on_headers_complete will tell parser that it should not - * expect neither a body nor any futher responses on this connection. This is - * useful for handling responses to a CONNECT request which may not contain - * `Upgrade` or `Connection: upgrade` headers. - * - * http_data_cb does not return data chunks. It will be called arbitrarily - * many times for each string. E.G. you might get 10 callbacks for "on_url" - * each providing just a few characters more data. - */ -typedef int (*http_data_cb) (http_parser*, const char *at, uint32_t length); -typedef int (*http_cb) (http_parser*); - - -/* Status Codes */ -#define HTTP_STATUS_MAP(XX) \ - XX(100, CONTINUE, Continue) \ - XX(101, SWITCHING_PROTOCOLS, Switching Protocols) \ - XX(102, PROCESSING, Processing) \ - XX(200, OK, OK) \ - XX(201, CREATED, Created) \ - XX(202, ACCEPTED, Accepted) \ - XX(203, NON_AUTHORITATIVE_INFORMATION, Non-Authoritative Information) \ - XX(204, NO_CONTENT, No Content) \ - XX(205, RESET_CONTENT, Reset Content) \ - XX(206, PARTIAL_CONTENT, Partial Content) \ - XX(207, MULTI_STATUS, Multi-Status) \ - XX(208, ALREADY_REPORTED, Already Reported) \ - XX(226, IM_USED, IM Used) \ - XX(300, MULTIPLE_CHOICES, Multiple Choices) \ - XX(301, MOVED_PERMANENTLY, Moved Permanently) \ - XX(302, FOUND, Found) \ - XX(303, SEE_OTHER, See Other) \ - XX(304, NOT_MODIFIED, Not Modified) \ - XX(305, USE_PROXY, Use Proxy) \ - XX(307, TEMPORARY_REDIRECT, Temporary Redirect) \ - XX(308, PERMANENT_REDIRECT, Permanent Redirect) \ - XX(400, BAD_REQUEST, Bad Request) \ - XX(401, UNAUTHORIZED, Unauthorized) \ - XX(402, PAYMENT_REQUIRED, Payment Required) \ - XX(403, FORBIDDEN, Forbidden) \ - XX(404, NOT_FOUND, Not Found) \ - XX(405, METHOD_NOT_ALLOWED, Method Not Allowed) \ - XX(406, NOT_ACCEPTABLE, Not Acceptable) \ - XX(407, PROXY_AUTHENTICATION_REQUIRED, Proxy Authentication Required) \ - XX(408, REQUEST_TIMEOUT, Request Timeout) \ - XX(409, CONFLICT, Conflict) \ - XX(410, GONE, Gone) \ - XX(411, LENGTH_REQUIRED, Length Required) \ - XX(412, PRECONDITION_FAILED, Precondition Failed) \ - XX(413, PAYLOAD_TOO_LARGE, Payload Too Large) \ - XX(414, URI_TOO_LONG, URI Too Long) \ - XX(415, UNSUPPORTED_MEDIA_TYPE, Unsupported Media Type) \ - XX(416, RANGE_NOT_SATISFIABLE, Range Not Satisfiable) \ - XX(417, EXPECTATION_FAILED, Expectation Failed) \ - XX(421, MISDIRECTED_REQUEST, Misdirected Request) \ - XX(422, UNPROCESSABLE_ENTITY, Unprocessable Entity) \ - XX(423, LOCKED, Locked) \ - XX(424, FAILED_DEPENDENCY, Failed Dependency) \ - XX(426, UPGRADE_REQUIRED, Upgrade Required) \ - XX(428, PRECONDITION_REQUIRED, Precondition Required) \ - XX(429, TOO_MANY_REQUESTS, Too Many Requests) \ - XX(431, REQUEST_HEADER_FIELDS_TOO_LARGE, Request Header Fields Too Large) \ - XX(451, UNAVAILABLE_FOR_LEGAL_REASONS, Unavailable For Legal Reasons) \ - XX(500, INTERNAL_SERVER_ERROR, Internal Server Error) \ - XX(501, NOT_IMPLEMENTED, Not Implemented) \ - XX(502, BAD_GATEWAY, Bad Gateway) \ - XX(503, SERVICE_UNAVAILABLE, Service Unavailable) \ - XX(504, GATEWAY_TIMEOUT, Gateway Timeout) \ - XX(505, HTTP_VERSION_NOT_SUPPORTED, HTTP Version Not Supported) \ - XX(506, VARIANT_ALSO_NEGOTIATES, Variant Also Negotiates) \ - XX(507, INSUFFICIENT_STORAGE, Insufficient Storage) \ - XX(508, LOOP_DETECTED, Loop Detected) \ - XX(510, NOT_EXTENDED, Not Extended) \ - XX(511, NETWORK_AUTHENTICATION_REQUIRED, Network Authentication Required) \ - -enum http_status - { -#define XX(num, name, string) HTTP_STATUS_##name = num, - HTTP_STATUS_MAP(XX) -#undef XX - }; - - -/* Request Methods */ -#define HTTP_METHOD_MAP(XX) \ - XX(0, DELETE, DELETE) \ - XX(1, GET, GET) \ - XX(2, HEAD, HEAD) \ - XX(3, POST, POST) \ - XX(4, PUT, PUT) \ - /* pathological */ \ - XX(5, CONNECT, CONNECT) \ - XX(6, OPTIONS, OPTIONS) \ - XX(7, TRACE, TRACE) \ - /* WebDAV */ \ - XX(8, COPY, COPY) \ - XX(9, LOCK, LOCK) \ - XX(10, MKCOL, MKCOL) \ - XX(11, MOVE, MOVE) \ - XX(12, PROPFIND, PROPFIND) \ - XX(13, PROPPATCH, PROPPATCH) \ - XX(14, SEARCH, SEARCH) \ - XX(15, UNLOCK, UNLOCK) \ - XX(16, BIND, BIND) \ - XX(17, REBIND, REBIND) \ - XX(18, UNBIND, UNBIND) \ - XX(19, ACL, ACL) \ - /* subversion */ \ - XX(20, REPORT, REPORT) \ - XX(21, MKACTIVITY, MKACTIVITY) \ - XX(22, CHECKOUT, CHECKOUT) \ - XX(23, MERGE, MERGE) \ - /* upnp */ \ - XX(24, MSEARCH, M-SEARCH) \ - XX(25, NOTIFY, NOTIFY) \ - XX(26, SUBSCRIBE, SUBSCRIBE) \ - XX(27, UNSUBSCRIBE, UNSUBSCRIBE) \ - /* RFC-5789 */ \ - XX(28, PATCH, PATCH) \ - XX(29, PURGE, PURGE) \ - /* CalDAV */ \ - XX(30, MKCALENDAR, MKCALENDAR) \ - /* RFC-2068, section 19.6.1.2 */ \ - XX(31, LINK, LINK) \ - XX(32, UNLINK, UNLINK) \ - -enum http_method - { -#define XX(num, name, string) HTTP_##name = num, - HTTP_METHOD_MAP(XX) -#undef XX - }; - - -enum http_parser_type { HTTP_REQUEST, HTTP_RESPONSE, HTTP_BOTH }; - - -/* Flag values for http_parser.flags field */ -enum flags - { F_CHUNKED = 1 << 0 - , F_CONNECTION_KEEP_ALIVE = 1 << 1 - , F_CONNECTION_CLOSE = 1 << 2 - , F_CONNECTION_UPGRADE = 1 << 3 - , F_TRAILING = 1 << 4 - , F_UPGRADE = 1 << 5 - , F_SKIPBODY = 1 << 6 - , F_CONTENTLENGTH = 1 << 7 - }; - - -/* Map for errno-related constants - * - * The provided argument should be a macro that takes 2 arguments. - */ -#define HTTP_ERRNO_MAP(XX) \ - /* No error */ \ - XX(OK, "success") \ - \ - /* Callback-related errors */ \ - XX(CB_message_begin, "the on_message_begin callback failed") \ - XX(CB_url, "the on_url callback failed") \ - XX(CB_header_field, "the on_header_field callback failed") \ - XX(CB_header_value, "the on_header_value callback failed") \ - XX(CB_headers_complete, "the on_headers_complete callback failed") \ - XX(CB_body, "the on_body callback failed") \ - XX(CB_message_complete, "the on_message_complete callback failed") \ - XX(CB_status, "the on_status callback failed") \ - XX(CB_chunk_header, "the on_chunk_header callback failed") \ - XX(CB_chunk_complete, "the on_chunk_complete callback failed") \ - \ - /* Parsing-related errors */ \ - XX(INVALID_EOF_STATE, "stream ended at an unexpected time") \ - XX(HEADER_OVERFLOW, \ - "too many header bytes seen; overflow detected") \ - XX(CLOSED_CONNECTION, \ - "data received after completed connection: close message") \ - XX(INVALID_VERSION, "invalid HTTP version") \ - XX(INVALID_STATUS, "invalid HTTP status code") \ - XX(INVALID_METHOD, "invalid HTTP method") \ - XX(INVALID_URL, "invalid URL") \ - XX(INVALID_HOST, "invalid host") \ - XX(INVALID_PORT, "invalid port") \ - XX(INVALID_PATH, "invalid path") \ - XX(INVALID_QUERY_STRING, "invalid query string") \ - XX(INVALID_FRAGMENT, "invalid fragment") \ - XX(LF_EXPECTED, "LF character expected") \ - XX(INVALID_HEADER_TOKEN, "invalid character in header") \ - XX(INVALID_CONTENT_LENGTH, \ - "invalid character in content-length header") \ - XX(UNEXPECTED_CONTENT_LENGTH, \ - "unexpected content-length header") \ - XX(INVALID_CHUNK_SIZE, \ - "invalid character in chunk size header") \ - XX(INVALID_CONSTANT, "invalid constant string") \ - XX(INVALID_INTERNAL_STATE, "encountered unexpected internal state")\ - XX(STRICT, "strict mode assertion failed") \ - XX(PAUSED, "parser is paused") \ - XX(UNKNOWN, "an unknown error occurred") - - -/* Define HPE_* values for each errno value above */ -#define HTTP_ERRNO_GEN(n, s) HPE_##n, -enum http_errno { - HTTP_ERRNO_MAP(HTTP_ERRNO_GEN) -}; -#undef HTTP_ERRNO_GEN - - -/* Get an http_errno value from an http_parser */ -#define HTTP_PARSER_ERRNO(p) ((enum http_errno) (p)->http_errno) - - -struct http_parser { - /** PRIVATE **/ - unsigned int type : 2; /* enum http_parser_type */ - unsigned int flags : 8; /* F_* values from 'flags' enum; semi-public */ - unsigned int state : 7; /* enum state from http_parser.c */ - unsigned int header_state : 7; /* enum header_state from http_parser.c */ - unsigned int index : 7; /* index into current matcher */ - unsigned int lenient_http_headers : 1; - - uint32_t nread; /* # bytes read in various scenarios */ - uint64_t content_length; /* # bytes in body (0 if no Content-Length header) */ - - /** READ-ONLY **/ - unsigned short http_major; - unsigned short http_minor; - unsigned int status_code : 16; /* responses only */ - unsigned int method : 8; /* requests only */ - unsigned int http_errno : 7; - - /* 1 = Upgrade header was present and the parser has exited because of that. - * 0 = No upgrade header present. - * Should be checked when http_parser_execute() returns in addition to - * error checking. - */ - unsigned int upgrade : 1; - - /** PUBLIC **/ - void *data; /* A pointer to get hook to the "connection" or "socket" object */ -}; - - -struct http_parser_settings { - http_cb on_message_begin; - http_data_cb on_url; - http_data_cb on_status; - http_data_cb on_header_field; - http_data_cb on_header_value; - http_cb on_headers_complete; - http_data_cb on_body; - http_cb on_message_complete; - /* When on_chunk_header is called, the current chunk length is stored - * in parser->content_length. - */ - http_cb on_chunk_header; - http_cb on_chunk_complete; -}; - enum http_parser_url_fields { UF_SCHEMA = 0 @@ -379,39 +82,6 @@ struct http_parser_url { */ unsigned long http_parser_version(void); -void http_parser_init(http_parser *parser, enum http_parser_type type); - - -/* Initialize http_parser_settings members to 0 - */ -void http_parser_settings_init(http_parser_settings *settings); - - -/* Executes the parser. Returns number of parsed bytes. Sets - * `parser->http_errno` on error. */ -uint32_t http_parser_execute(http_parser *parser, - const http_parser_settings *settings, - const char *data, - uint32_t len); - - -/* If http_should_keep_alive() in the on_headers_complete or - * on_message_complete callback returns 0, then this should be - * the last message on the connection. - * If you are the server, respond with the "Connection: close" header. - * If you are the client, close the connection. - */ -int http_should_keep_alive(const http_parser *parser); - -/* Returns a string version of the HTTP method. */ -const char *http_method_str(enum http_method m); - -/* Return a string name of the given error */ -const char *http_errno_name(enum http_errno err); - -/* Return a string description of the given error */ -const char *http_errno_description(enum http_errno err); - /* Initialize all http_parser_url members to 0 */ void http_parser_url_init(struct http_parser_url *u); @@ -420,12 +90,6 @@ int http_parser_parse_url(const char *buf, uint32_t buflen, int is_connect, struct http_parser_url *u); -/* Pause or un-pause the parser; a nonzero value pauses */ -void http_parser_pause(http_parser *parser, int paused); - -/* Checks if this is the final chunk of the body. */ -int http_body_is_final(const http_parser *parser); - #ifdef __cplusplus } #endif From e5db3b5880a63522db4708fc653920b79a694477 Mon Sep 17 00:00:00 2001 From: Andrea Gilardoni Date: Wed, 21 Feb 2024 15:32:21 +0100 Subject: [PATCH 37/50] imported wrapper class for url parsing --- src/URLParser.h | 94 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 94 insertions(+) create mode 100644 src/URLParser.h diff --git a/src/URLParser.h b/src/URLParser.h new file mode 100644 index 0000000..eaac7e9 --- /dev/null +++ b/src/URLParser.h @@ -0,0 +1,94 @@ +/* + * PackageLicenseDeclared: Apache-2.0 + * Copyright (c) 2017 ARM Limited + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +#ifndef _MBED_HTTP_PARSED_URL_H_ +#define _MBED_HTTP_PARSED_URL_H_ + +#include "utility/http_parser.h" + +class ParsedUrl { +public: + ParsedUrl(const char* url) { + struct http_parser_url parsed_url; + http_parser_parse_url(url, strlen(url), false, &parsed_url); + + for (size_t ix = 0; ix < UF_MAX; ix++) { + char* value; + if (parsed_url.field_set & (1 << ix)) { + value = (char*)calloc(parsed_url.field_data[ix].len + 1, 1); + memcpy(value, url + parsed_url.field_data[ix].off, + parsed_url.field_data[ix].len); + } + else { + value = (char*)calloc(1, 1); + } + + switch ((http_parser_url_fields)ix) { + case UF_SCHEMA: _schema = value; break; + case UF_HOST: _host = value; break; + case UF_PATH: _path = value; break; + case UF_QUERY: _query = value; break; + case UF_USERINFO: _userinfo = value; break; + default: + // PORT is already parsed, FRAGMENT is not relevant for HTTP requests + free(value); + break; + } + } + + _port = parsed_url.port; + if (!_port) { + if (strcmp(_schema, "https") == 0 || strcmp(_schema, "wss") == 0) { + _port = 443; + } + else { + _port = 80; + } + } + + if (strcmp(_path, "") == 0) { + free(_path); + _path = (char*)calloc(2, 1); + _path[0] = '/'; + } + } + + ~ParsedUrl() { + if (_schema) free(_schema); + if (_host) free(_host); + if (_path) free(_path); + if (_query) free(_query); + if (_userinfo) free(_userinfo); + } + + uint16_t port() const { return _port; } + char* schema() const { return _schema; } + char* host() const { return _host; } + char* path() const { return _path; } + char* query() const { return _query; } + char* userinfo() const { return _userinfo; } + +private: + uint16_t _port; + char* _schema; + char* _host; + char* _path; + char* _query; + char* _userinfo; +}; + +#endif // _MBED_HTTP_PARSED_URL_H_ From a1a79a59157f2c191229bf2729e038cfcf1bfe39 Mon Sep 17 00:00:00 2001 From: Andrea Gilardoni Date: Wed, 21 Feb 2024 16:25:42 +0100 Subject: [PATCH 38/50] added example for url parsing --- examples/ParseURL/ParseURL.ino | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) create mode 100644 examples/ParseURL/ParseURL.ino diff --git a/examples/ParseURL/ParseURL.ino b/examples/ParseURL/ParseURL.ino new file mode 100644 index 0000000..f69a2bc --- /dev/null +++ b/examples/ParseURL/ParseURL.ino @@ -0,0 +1,29 @@ +#include "URLParser.h" + +void setup() { + + Serial.begin(9600); + + while(!Serial); + + Serial.println("starting"); + + ParsedUrl url( + "https://www.google.com/search?q=arduino" + ); + + Serial.print("parsed url schema: \""); + Serial.print(url.schema()); + Serial.print("\"\nparsed url host: \""); + Serial.print(url.host()); + Serial.print("\"\nparsed url path: \""); + Serial.print(url.path()); + Serial.print("\"\nparsed url query: \""); + Serial.print(url.query()); + Serial.print("\"\nparsed url userinfo: \""); + Serial.print(url.userinfo()); + Serial.println("\""); + +} + +void loop() { } \ No newline at end of file From 9f01bfe879b149c312473c8f9da976c46542a241 Mon Sep 17 00:00:00 2001 From: Alexander Entinger Date: Wed, 21 Feb 2024 18:57:17 +0100 Subject: [PATCH 39/50] Revert "Fix regression: report size delta size on PR. (#172)" This reverts commit 7a6b39a1af31c175c7e999ac366f52b6a3efcba4. --- .github/workflows/compile-examples.yml | 27 ++++-------------------- .github/workflows/report-size-deltas.yml | 24 +++++++++++++++++++++ .gitignore | 1 - 3 files changed, 28 insertions(+), 24 deletions(-) create mode 100644 .github/workflows/report-size-deltas.yml diff --git a/.github/workflows/compile-examples.yml b/.github/workflows/compile-examples.yml index d7a183e..0dd5ac7 100644 --- a/.github/workflows/compile-examples.yml +++ b/.github/workflows/compile-examples.yml @@ -18,15 +18,14 @@ on: workflow_dispatch: repository_dispatch: -env: - # It's convenient to set variables for values used multiple times in the workflow. - SKETCHES_REPORTS_PATH: sketches-reports - jobs: - compile: + build: name: ${{ matrix.board.fqbn }} runs-on: ubuntu-latest + env: + SKETCHES_REPORTS_PATH: sketches-reports + strategy: fail-fast: false @@ -62,21 +61,3 @@ jobs: if-no-files-found: error path: ${{ env.SKETCHES_REPORTS_PATH }} name: sketches-report-${{ matrix.board.artifact-name-suffix }} - - # When using a matrix to compile for multiple boards, it's necessary to use a separate job for the deltas report - report: - needs: compile # Wait for the compile job to finish to get the data for the report - if: github.event_name == 'pull_request' # Only run the job when the workflow is triggered by a pull request - runs-on: ubuntu-latest - - steps: - # This step is needed to get the size data produced by the compile jobs - - name: Download sketches reports artifacts - uses: actions/download-artifact@v4 - with: - # All workflow artifacts will be downloaded to this location. - path: ${{ env.SKETCHES_REPORTS_PATH }} - - - uses: arduino/report-size-deltas@v1 - with: - sketches-reports-source: ${{ env.SKETCHES_REPORTS_PATH }} diff --git a/.github/workflows/report-size-deltas.yml b/.github/workflows/report-size-deltas.yml new file mode 100644 index 0000000..652be5d --- /dev/null +++ b/.github/workflows/report-size-deltas.yml @@ -0,0 +1,24 @@ +name: Report Size Deltas + +# See: https://docs.github.com/en/free-pro-team@latest/actions/reference/events-that-trigger-workflows +on: + push: + paths: + - ".github/workflows/report-size-deltas.yml" + schedule: + # Run at the minimum interval allowed by GitHub Actions. + # Note: GitHub Actions periodically has outages which result in workflow failures. + # In this event, the workflows will start passing again once the service recovers. + - cron: "*/5 * * * *" + workflow_dispatch: + repository_dispatch: + +jobs: + report: + runs-on: ubuntu-latest + steps: + - name: Comment size deltas reports to PRs + uses: arduino/report-size-deltas@v1 + with: + # The name of the workflow artifact created by the sketch compilation workflow + sketches-reports-source: sketches-reports diff --git a/.gitignore b/.gitignore index 24a0007..653acab 100644 --- a/.gitignore +++ b/.gitignore @@ -3,4 +3,3 @@ examples/node_test_server/node_modules/ *.DS_Store */.DS_Store examples/.DS_Store -.idea/ From 8c7bff748a40d3bfdf214104b2bba6acceba3ee7 Mon Sep 17 00:00:00 2001 From: Alexander Entinger Date: Wed, 21 Feb 2024 18:57:45 +0100 Subject: [PATCH 40/50] Correct workflow artifact name pattern in size deltas report workflow The "sketches-reports-source" input of the "arduino/report-size-deltas" GitHub Actions action defines the regular expression that matches the names of the sketches report workflow artifacts produced by the "Compile Examples" workflow. The key string in the names of these artifacts was set to "sketches-report" when the "Compile Examples" workflow was adjusted for compatibility with the breaking changes introduced by updating to version 4.x of the workflow's "actions/upload-artifact" GitHub Actions action dependency. The pattern set in the size deltas report workflow was "sketches-reports". The "s" at the end of that pattern caused it to no longer match against the key string in the artifact names after that adjustment of the "Compile Examples" workflow, resulting in size deltas reports no longer being generated by the workflow. Although a minimal fix would be to simply remove the "s" from the end of the pattern, the decision was made to use a more strict regular expression. This will make it easier for maintainers and contributors to understand that this value is a regular expression and the exact nature of how that regular expression functions (which is less clear when relying on the "arduino/report-size-deltas" action's partial pattern matching behavior). --- .github/workflows/report-size-deltas.yml | 4 ++-- .gitignore | 1 + 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/.github/workflows/report-size-deltas.yml b/.github/workflows/report-size-deltas.yml index 652be5d..39e2a0a 100644 --- a/.github/workflows/report-size-deltas.yml +++ b/.github/workflows/report-size-deltas.yml @@ -20,5 +20,5 @@ jobs: - name: Comment size deltas reports to PRs uses: arduino/report-size-deltas@v1 with: - # The name of the workflow artifact created by the sketch compilation workflow - sketches-reports-source: sketches-reports + # Regex matching the names of the workflow artifacts created by the "Compile Examples" workflow + sketches-reports-source: ^sketches-report-.+ diff --git a/.gitignore b/.gitignore index 653acab..24a0007 100644 --- a/.gitignore +++ b/.gitignore @@ -3,3 +3,4 @@ examples/node_test_server/node_modules/ *.DS_Store */.DS_Store examples/.DS_Store +.idea/ From 8d44059cd5bdeccb29726ec53c796c85501f5caf Mon Sep 17 00:00:00 2001 From: Andrea Gilardoni <4046444+andreagilardoni@users.noreply.github.com> Date: Wed, 13 Mar 2024 10:48:08 +0100 Subject: [PATCH 41/50] Update examples/ParseURL/ParseURL.ino Co-authored-by: per1234 --- examples/ParseURL/ParseURL.ino | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/examples/ParseURL/ParseURL.ino b/examples/ParseURL/ParseURL.ino index f69a2bc..410ac85 100644 --- a/examples/ParseURL/ParseURL.ino +++ b/examples/ParseURL/ParseURL.ino @@ -12,15 +12,15 @@ void setup() { "https://www.google.com/search?q=arduino" ); - Serial.print("parsed url schema: \""); + Serial.print("parsed URL schema: \""); Serial.print(url.schema()); - Serial.print("\"\nparsed url host: \""); + Serial.print("\"\nparsed URL host: \""); Serial.print(url.host()); - Serial.print("\"\nparsed url path: \""); + Serial.print("\"\nparsed URL path: \""); Serial.print(url.path()); - Serial.print("\"\nparsed url query: \""); + Serial.print("\"\nparsed URL query: \""); Serial.print(url.query()); - Serial.print("\"\nparsed url userinfo: \""); + Serial.print("\"\nparsed URL userinfo: \""); Serial.print(url.userinfo()); Serial.println("\""); From dbe65d631e46e1f829d9aee8375614477a8b138e Mon Sep 17 00:00:00 2001 From: Andrea Gilardoni Date: Mon, 4 Mar 2024 16:43:13 +0100 Subject: [PATCH 42/50] added include preprocessor for boards compatibility --- src/URLParser.h | 14 ++++++++++++++ src/utility/http_parser.c | 9 +++++++++ 2 files changed, 23 insertions(+) diff --git a/src/URLParser.h b/src/URLParser.h index eaac7e9..0424592 100644 --- a/src/URLParser.h +++ b/src/URLParser.h @@ -15,6 +15,18 @@ * limitations under the License. */ +/* + * The following class is defined in mbed libraries, in case of STM32H7 include the original library + */ +#if defined __has_include +# if __has_include() +# include +# else +# define NO_HTTP_PARSED +# endif +#endif + +#ifdef NO_HTTP_PARSED #ifndef _MBED_HTTP_PARSED_URL_H_ #define _MBED_HTTP_PARSED_URL_H_ @@ -92,3 +104,5 @@ class ParsedUrl { }; #endif // _MBED_HTTP_PARSED_URL_H_ +#endif // NO_HTTP_PARSED +#undef NO_HTTP_PARSED \ No newline at end of file diff --git a/src/utility/http_parser.c b/src/utility/http_parser.c index f1be647..a572a4c 100644 --- a/src/utility/http_parser.c +++ b/src/utility/http_parser.c @@ -1,3 +1,10 @@ +#if defined __has_include +# if ! __has_include() && ! __has_include() +# define NO_HTTP_PARSER +# endif +#endif + +#ifdef NO_HTTP_PARSER /* Based on src/http/ngx_http_parse.c from NGINX copyright Igor Sysoev * * Additional changes are licensed under the same terms as NGINX and @@ -580,3 +587,5 @@ http_parser_version(void) { HTTP_PARSER_VERSION_MINOR * 0x00100 | HTTP_PARSER_VERSION_PATCH * 0x00001; } + +#endif // NO_HTTP_PARSER \ No newline at end of file From 734f5b58a9fc4920eebfa063466434ef4c7ed486 Mon Sep 17 00:00:00 2001 From: Andrea Gilardoni Date: Wed, 13 Mar 2024 10:43:48 +0100 Subject: [PATCH 43/50] fixing codespell ci for imported url lib --- .codespellrc | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.codespellrc b/.codespellrc index 101edae..2fcb936 100644 --- a/.codespellrc +++ b/.codespellrc @@ -4,4 +4,4 @@ ignore-words-list = , check-filenames = check-hidden = -skip = ./.git +skip = ./.git,./src/utility \ No newline at end of file From 482e088f93c09a62a5aa56fbe946534a94344e69 Mon Sep 17 00:00:00 2001 From: Andrea Gilardoni Date: Thu, 14 Mar 2024 14:39:25 +0100 Subject: [PATCH 44/50] added README for imported library --- src/utility/README.md | 5 +++++ 1 file changed, 5 insertions(+) create mode 100644 src/utility/README.md diff --git a/src/utility/README.md b/src/utility/README.md new file mode 100644 index 0000000..56f8c96 --- /dev/null +++ b/src/utility/README.md @@ -0,0 +1,5 @@ +# http_parser library + +This code is imported from: https://github.com/arduino/ArduinoCore-mbed/tree/4.1.1/libraries/SocketWrapper/src/utility/http_parser + +The code is shrinked in size by deleting all the unrelated code to url parse. From 9ea6ace0d031396107d38cdb427ac01ae2b5c021 Mon Sep 17 00:00:00 2001 From: Andrea Gilardoni Date: Wed, 13 Mar 2024 13:29:03 +0100 Subject: [PATCH 45/50] moving http_parser from utility to utility/URLParser --- .codespellrc | 2 +- src/URLParser.h | 2 +- src/utility/{ => URLParser}/LICENSE | 0 src/utility/{ => URLParser}/README.md | 0 src/utility/{ => URLParser}/http_parser.c | 0 src/utility/{ => URLParser}/http_parser.h | 0 6 files changed, 2 insertions(+), 2 deletions(-) rename src/utility/{ => URLParser}/LICENSE (100%) rename src/utility/{ => URLParser}/README.md (100%) rename src/utility/{ => URLParser}/http_parser.c (100%) rename src/utility/{ => URLParser}/http_parser.h (100%) diff --git a/.codespellrc b/.codespellrc index 2fcb936..c5233c0 100644 --- a/.codespellrc +++ b/.codespellrc @@ -4,4 +4,4 @@ ignore-words-list = , check-filenames = check-hidden = -skip = ./.git,./src/utility \ No newline at end of file +skip = ./.git,./src/utility/URLParser diff --git a/src/URLParser.h b/src/URLParser.h index 0424592..fd31e93 100644 --- a/src/URLParser.h +++ b/src/URLParser.h @@ -30,7 +30,7 @@ #ifndef _MBED_HTTP_PARSED_URL_H_ #define _MBED_HTTP_PARSED_URL_H_ -#include "utility/http_parser.h" +#include "utility/URLParser/http_parser.h" class ParsedUrl { public: diff --git a/src/utility/LICENSE b/src/utility/URLParser/LICENSE similarity index 100% rename from src/utility/LICENSE rename to src/utility/URLParser/LICENSE diff --git a/src/utility/README.md b/src/utility/URLParser/README.md similarity index 100% rename from src/utility/README.md rename to src/utility/URLParser/README.md diff --git a/src/utility/http_parser.c b/src/utility/URLParser/http_parser.c similarity index 100% rename from src/utility/http_parser.c rename to src/utility/URLParser/http_parser.c diff --git a/src/utility/http_parser.h b/src/utility/URLParser/http_parser.h similarity index 100% rename from src/utility/http_parser.h rename to src/utility/URLParser/http_parser.h From 9101851c3b9c7b19434b822ddbc627fa3eb8dc12 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Tue, 19 Mar 2024 14:48:22 +0100 Subject: [PATCH 46/50] Bump geekyeggo/delete-artifact from 4 to 5 (#175) Bumps [geekyeggo/delete-artifact](https://github.com/geekyeggo/delete-artifact) from 4 to 5. - [Release notes](https://github.com/geekyeggo/delete-artifact/releases) - [Changelog](https://github.com/GeekyEggo/delete-artifact/blob/main/CHANGELOG.md) - [Commits](https://github.com/geekyeggo/delete-artifact/compare/v4...v5) --- updated-dependencies: - dependency-name: geekyeggo/delete-artifact dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> --- .github/workflows/sync-labels.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/sync-labels.yml b/.github/workflows/sync-labels.yml index 47ac50a..53a9f54 100644 --- a/.github/workflows/sync-labels.yml +++ b/.github/workflows/sync-labels.yml @@ -114,7 +114,7 @@ jobs: path: ${{ env.CONFIGURATIONS_FOLDER }} - name: Remove unneeded artifact - uses: geekyeggo/delete-artifact@v4 + uses: geekyeggo/delete-artifact@v5 with: name: ${{ env.CONFIGURATIONS_ARTIFACT }} From 6f2659de4c0523f0a5fa4bc1154d1e5dc1b01546 Mon Sep 17 00:00:00 2001 From: Andrea Gilardoni <4046444+andreagilardoni@users.noreply.github.com> Date: Tue, 26 Mar 2024 10:25:16 +0100 Subject: [PATCH 47/50] Release v0.6.0 --- library.properties | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/library.properties b/library.properties index 3b7307e..e33fe6e 100644 --- a/library.properties +++ b/library.properties @@ -1,5 +1,5 @@ name=ArduinoHttpClient -version=0.5.0 +version=0.6.0 author=Arduino maintainer=Arduino sentence=[EXPERIMENTAL] Easily interact with web servers from Arduino, using HTTP and WebSockets. From 1a3fb989a5d92575a05b6ac3627de554723709ac Mon Sep 17 00:00:00 2001 From: Martino Facchin Date: Wed, 8 May 2024 17:25:48 +0200 Subject: [PATCH 48/50] Make sure iContentLength doesn't wrap around due to malformed packets --- src/HttpClient.cpp | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/src/HttpClient.cpp b/src/HttpClient.cpp index c0f5c27..31909d9 100644 --- a/src/HttpClient.cpp +++ b/src/HttpClient.cpp @@ -819,7 +819,11 @@ int HttpClient::readHeader() case eReadingContentLength: if (isdigit(c)) { - iContentLength = iContentLength*10 + (c - '0'); + long _iContentLength = iContentLength*10 + (c - '0'); + // Only apply if the value didn't wrap around + if (_iContentLength > iContentLength) { + iContentLength = _iContentLength; + } } else { From 657e2b08d984168f95ad0a552de56d3f0d27a83b Mon Sep 17 00:00:00 2001 From: Martino Facchin Date: Thu, 25 Jul 2024 12:04:37 +0200 Subject: [PATCH 49/50] Release 0.6.1 --- library.properties | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/library.properties b/library.properties index e33fe6e..c93d0de 100644 --- a/library.properties +++ b/library.properties @@ -1,5 +1,5 @@ name=ArduinoHttpClient -version=0.6.0 +version=0.6.1 author=Arduino maintainer=Arduino sentence=[EXPERIMENTAL] Easily interact with web servers from Arduino, using HTTP and WebSockets. From 54627fcb18d92e0b2b8499a73e2c65f4ded9d6d6 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Tue, 8 Oct 2024 17:20:59 +0000 Subject: [PATCH 50/50] Bump arduino/arduino-lint-action from 1 to 2 Bumps [arduino/arduino-lint-action](https://github.com/arduino/arduino-lint-action) from 1 to 2. - [Release notes](https://github.com/arduino/arduino-lint-action/releases) - [Commits](https://github.com/arduino/arduino-lint-action/compare/v1...v2) --- updated-dependencies: - dependency-name: arduino/arduino-lint-action dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] --- .github/workflows/check-arduino.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/check-arduino.yml b/.github/workflows/check-arduino.yml index adb330f..e818685 100644 --- a/.github/workflows/check-arduino.yml +++ b/.github/workflows/check-arduino.yml @@ -19,7 +19,7 @@ jobs: uses: actions/checkout@v4 - name: Arduino Lint - uses: arduino/arduino-lint-action@v1 + uses: arduino/arduino-lint-action@v2 with: compliance: specification library-manager: update