http_parser.rb 0.5.1-x86-mswin32-60 → 0.5.2-x86-mswin32-60

data/ext/ruby_http_parser/vendor/http-parser-java/TODO

@@ -1,3 +1,6 @@
+some tests from test.c left to port
+documentation
+
 hi level callback interface 
 eventloop
 state() as a function (?)

data/ext/ruby_http_parser/vendor/http-parser-java/build.xml

@@ -0,0 +1,74 @@
+<?xml version="1.0"?>
+
+<project name="http-parser" default="compile" basedir=".">
+
+<echo message="pulling in property files"/>
+<property file="build.properties"/>
+<property name="classes.dir" value="classes"/>
+<property name="assemble.dir" value="assemble"/>
+<property name="lib.dir" value="lib"/>
+
+
+
+<target name="prepare">
+  <mkdir dir="${classes.dir}" />
+  <mkdir dir="${assemble.dir}" />
+  <mkdir dir="${lib.dir}" />
+</target>
+
+<target name="clean">
+	<delete dir="${classes.dir}"/>
+	<delete dir="lib"/>
+	<delete dir="doc"/>
+	<delete dir="${assemble.dir}"/>
+</target>
+
+<target name="compile" depends="prepare">
+  <javac srcdir="src" destdir="${classes.dir}" debug='true'>
+    <classpath>
+      <pathelement path="${classpath}"/>
+      <pathelement location="ext/http-parser.jar"/>
+      <pathelement location="ext/primitives.jar"/>
+    </classpath>
+  </javac>
+</target>
+
+<target name="jar" depends="compile">
+	<copy todir="${assemble.dir}">
+		<fileset dir="classes"/>
+	</copy>
+	<jar basedir="${assemble.dir}" destfile="lib/${ant.project.name}.jar"/>
+</target>
+
+<target name="run" depends="jar">
+	<echo message="don't know how to run"/>
+</target>
+
+<target name="doc" depends="prepare">
+  <javadoc sourcepath="src/impl" destdir="doc">  
+	</javadoc>
+</target>
+
+<target name="test_permutations" depends="compile">
+  <java classname="http_parser.lolevel.TestLoaderNG">
+    <arg value="tests.dumped"/>
+    <classpath>
+      <pathelement location="classes/"/>
+      <pathelement location="ext/primitives.jar/"/>
+    </classpath> 
+  </java>
+</target>
+
+<target name="test_unit" depends="compile">
+  <java classname="http_parser.lolevel.Test">
+    <arg value="tests.dumped"/>
+    <classpath>
+      <pathelement location="classes/"/>
+      <pathelement location="ext/primitives.jar/"/>
+    </classpath> 
+  </java>
+</target>
+
+<target name="test" depends="test_permutations, test_unit"/>
+
+</project>

data/ext/ruby_http_parser/vendor/http-parser-java/http_parser.c

@@ -1,4 +1,4 @@
-/* Copyright 2009,2010 Ryan Dahl <ry@tinyclouds.org>
+/* 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
@@ -19,16 +19,6 @@
  * IN THE SOFTWARE.
  */
 #include <http_parser.h>
-#ifdef _WIN32
-typedef __int8 int8_t;
-typedef unsigned __int8 uint8_t;
-typedef __int16 int16_t;
-typedef unsigned __int16 uint16_t;
-typedef __int16 int32_t;
-typedef unsigned __int32 uint32_t;
-#else
-#include <stdint.h>
-#endif
 #include <assert.h>
 #include <stddef.h>
 
@@ -103,12 +93,21 @@ static const char *method_strings[] =
   , "MKACTIVITY"
   , "CHECKOUT"
   , "MERGE"
+  , "M-SEARCH"
+  , "NOTIFY"
+  , "SUBSCRIBE"
+  , "UNSUBSCRIBE"
   };
 
 
-/* ' ', '_', '-' and all alpha-numeric ascii characters are accepted by acceptable_header.
-   The 'A'-'Z' are lower-cased.  */
-static const char acceptable_header[256] = {
+/* Tokens as defined by rfc 2616. Also lowercases them.
+ *        token       = 1*<any CHAR except CTLs or separators>
+ *     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   */
@@ -118,9 +117,9 @@ static const char acceptable_header[256] = {
 /*  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,       0,       0,       0,       0,       0,
+       ' ',      '!',     '"',     '#',     '$',     '%',     '&',    '\'',
 /*  40  (    41  )    42  *    43  +    44  ,    45  -    46  .    47  /  */
-        0,       0,       0,       0,       0,      '-',      0,       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  ?  */
@@ -132,15 +131,15 @@ static const char acceptable_header[256] = {
 /*  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,       0,      '_',
+       'x',     'y',     'z',      0,       0,       0,      '^',     '_',
 /*  96  `    97  a    98  b    99  c   100  d   101  e   102  f   103  g  */
-        0,      'a',     'b',     'c',     'd',     'e',     'f',     '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,       0,       0 };
+       'x',     'y',     'z',      0,      '|',     '}',     '~',       0 };
 
 
 static const int8_t unhex[256] =
@@ -187,7 +186,28 @@ static const uint8_t normal_url_char[256] = {
 /* 112  p   113  q   114  r   115  s   116  t   117  u   118  v   119  w  */
         1,       1,       1,       1,       1,       1,       1,       1,
 /* 120  x   121  y   122  z   123  {   124  |   125  }   126  ~   127 del */
-        1,       1,       1,       1,       1,       1,       1,       0 };
+        1,       1,       1,       1,       1,       1,       1,       0,
+
+/* Remainder of non-ASCII range are accepted as-is to support implicitly UTF-8
+   encoded paths. This is out of spec, but clients generate this and most other
+   HTTP servers support it. We should, too. */
+
+        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,
+        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,
+        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 };
 
 
 enum state
@@ -241,15 +261,17 @@ enum state
 
   , s_header_almost_done
 
+  , s_chunk_size_start
+  , s_chunk_size
+  , s_chunk_parameters
+  , s_chunk_size_almost_done
+  
   , s_headers_almost_done
   /* Important: 's_headers_almost_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_size_start
-  , s_chunk_size
-  , s_chunk_size_almost_done
-  , s_chunk_parameters
+
   , s_chunk_data
   , s_chunk_data_almost_done
   , s_chunk_data_done
@@ -259,7 +281,7 @@ enum state
   };
 
 
-#define PARSING_HEADER(state) (state <= s_headers_almost_done && 0 == (parser->flags & F_TRAILING))
+#define PARSING_HEADER(state) (state <= s_headers_almost_done)
 
 
 enum header_states
@@ -302,6 +324,7 @@ enum flags
 #define CR '\r'
 #define LF '\n'
 #define LOWER(c) (unsigned char)(c | 0x20)
+#define TOKEN(c) tokens[(unsigned char)c]
 
 
 #define start_state (parser->type == HTTP_REQUEST ? s_start_req : s_start_res)
@@ -331,10 +354,20 @@ size_t http_parser_execute (http_parser *parser,
   uint64_t nread = parser->nread;
 
   if (len == 0) {
-    if (state == s_body_identity_eof) {
-      CALLBACK2(message_complete);
+    switch (state) {
+      case s_body_identity_eof:
+        CALLBACK2(message_complete);
+        return 0;
+
+      case s_dead:
+      case s_start_req_or_res:
+      case s_start_res:
+      case s_start_req:
+        return 0;
+
+      default:
+        return 1; // error
     }
-    return 0;
   }
 
   /* technically we could combine all of these (except for url_mark) into one
@@ -579,12 +612,14 @@ size_t http_parser_execute (http_parser *parser,
           case 'G': parser->method = HTTP_GET; break;
           case 'H': parser->method = HTTP_HEAD; break;
           case 'L': parser->method = HTTP_LOCK; break;
-          case 'M': parser->method = HTTP_MKCOL; /* or MOVE, MKACTIVITY, MERGE */ break;
+          case 'M': parser->method = HTTP_MKCOL; /* or MOVE, MKACTIVITY, MERGE, M-SEARCH */ break;
+          case 'N': parser->method = HTTP_NOTIFY; break;
           case 'O': parser->method = HTTP_OPTIONS; break;
           case 'P': parser->method = HTTP_POST; /* or PROPFIND or PROPPATCH or PUT */ break;
           case 'R': parser->method = HTTP_REPORT; break;
+          case 'S': parser->method = HTTP_SUBSCRIBE; break;
           case 'T': parser->method = HTTP_TRACE; break;
-          case 'U': parser->method = HTTP_UNLOCK; break;
+          case 'U': parser->method = HTTP_UNLOCK; /* or UNSUBSCRIBE */ break;
           default: goto error;
         }
         state = s_req_method;
@@ -612,6 +647,8 @@ size_t http_parser_execute (http_parser *parser,
             parser->method = HTTP_MOVE;
           } else if (index == 1 && ch == 'E') {
             parser->method = HTTP_MERGE;
+          } else if (index == 1 && ch == '-') {
+            parser->method = HTTP_MSEARCH;
           } else if (index == 2 && ch == 'A') {
             parser->method = HTTP_MKACTIVITY;
           }
@@ -619,6 +656,8 @@ size_t http_parser_execute (http_parser *parser,
           parser->method = HTTP_PROPFIND; /* or HTTP_PROPPATCH */
         } else if (index == 1 && parser->method == HTTP_POST && ch == 'U') {
           parser->method = HTTP_PUT;
+        } else if (index == 2 && parser->method == HTTP_UNLOCK && ch == 'S') {
+          parser->method = HTTP_UNSUBSCRIBE;
         } else if (index == 4 && parser->method == HTTP_PROPFIND && ch == 'P') {
           parser->method = HTTP_PROPPATCH;
         } else {
@@ -632,7 +671,7 @@ size_t http_parser_execute (http_parser *parser,
       {
         if (ch == ' ') break;
 
-        if (ch == '/') {
+        if (ch == '/' || ch == '*') {
           MARK(url);
           MARK(path);
           state = s_req_path;
@@ -662,6 +701,9 @@ size_t http_parser_execute (http_parser *parser,
         } else if (ch == '.') {
           state = s_req_host;
           break;
+        } else if ('0' <= ch && ch <= '9') {
+          state = s_req_host;
+          break;
         }
 
         goto error;
@@ -698,6 +740,9 @@ size_t http_parser_execute (http_parser *parser,
             CALLBACK(url);
             state = s_req_http_start;
             break;
+          case '?':
+            state = s_req_query_string_start;
+            break;
           default:
             goto error;
         }
@@ -720,6 +765,9 @@ size_t http_parser_execute (http_parser *parser,
             CALLBACK(url);
             state = s_req_http_start;
             break;
+          case '?':
+            state = s_req_query_string_start;
+            break;
           default:
             goto error;
         }
@@ -739,12 +787,14 @@ size_t http_parser_execute (http_parser *parser,
           case CR:
             CALLBACK(url);
             CALLBACK(path);
+            parser->http_major = 0;
             parser->http_minor = 9;
             state = s_req_line_almost_done;
             break;
           case LF:
             CALLBACK(url);
             CALLBACK(path);
+            parser->http_major = 0;
             parser->http_minor = 9;
             state = s_header_field_start;
             break;
@@ -779,11 +829,13 @@ size_t http_parser_execute (http_parser *parser,
             break;
           case CR:
             CALLBACK(url);
+            parser->http_major = 0;
             parser->http_minor = 9;
             state = s_req_line_almost_done;
             break;
           case LF:
             CALLBACK(url);
+            parser->http_major = 0;
             parser->http_minor = 9;
             state = s_header_field_start;
             break;
@@ -812,12 +864,14 @@ size_t http_parser_execute (http_parser *parser,
           case CR:
             CALLBACK(url);
             CALLBACK(query_string);
+            parser->http_major = 0;
             parser->http_minor = 9;
             state = s_req_line_almost_done;
             break;
           case LF:
             CALLBACK(url);
             CALLBACK(query_string);
+            parser->http_major = 0;
             parser->http_minor = 9;
             state = s_header_field_start;
             break;
@@ -846,11 +900,13 @@ size_t http_parser_execute (http_parser *parser,
             break;
           case CR:
             CALLBACK(url);
+            parser->http_major = 0;
             parser->http_minor = 9;
             state = s_req_line_almost_done;
             break;
           case LF:
             CALLBACK(url);
+            parser->http_major = 0;
             parser->http_minor = 9;
             state = s_header_field_start;
             break;
@@ -879,12 +935,14 @@ size_t http_parser_execute (http_parser *parser,
           case CR:
             CALLBACK(url);
             CALLBACK(fragment);
+            parser->http_major = 0;
             parser->http_minor = 9;
             state = s_req_line_almost_done;
             break;
           case LF:
             CALLBACK(url);
             CALLBACK(fragment);
+            parser->http_major = 0;
             parser->http_minor = 9;
             state = s_header_field_start;
             break;
@@ -1006,9 +1064,9 @@ size_t http_parser_execute (http_parser *parser,
           goto headers_almost_done;
         }
 
-        c = LOWER(ch);
+        c = TOKEN(ch);
 
-        if (c < 'a' || 'z' < c) goto error;
+        if (!c) goto error;
 
         MARK(header_field);
 
@@ -1041,7 +1099,7 @@ size_t http_parser_execute (http_parser *parser,
 
       case s_header_field:
       {
-        c = acceptable_header[(unsigned char)ch];
+        c = TOKEN(ch);
 
         if (c) {
           switch (header_state) {
@@ -1177,23 +1235,18 @@ size_t http_parser_execute (http_parser *parser,
         state = s_header_value;
         index = 0;
 
-        c = acceptable_header[(unsigned char)ch];
-
-        if (!c) {
-          if (ch == CR) {
-            CALLBACK(header_value);
-            header_state = h_general;
-            state = s_header_almost_done;
-            break;
-          }
-
-          if (ch == LF) {
-            CALLBACK(header_value);
-            state = s_header_field_start;
-            break;
-          }
+        c = LOWER(ch);
 
+        if (ch == CR) {
+          CALLBACK(header_value);
           header_state = h_general;
+          state = s_header_almost_done;
+          break;
+        }
+
+        if (ch == LF) {
+          CALLBACK(header_value);
+          state = s_header_field_start;
           break;
         }
 
@@ -1238,22 +1291,19 @@ size_t http_parser_execute (http_parser *parser,
 
       case s_header_value:
       {
-        c = acceptable_header[(unsigned char)ch];
-
-        if (!c) {
-          if (ch == CR) {
-            CALLBACK(header_value);
-            state = s_header_almost_done;
-            break;
-          }
+        c = LOWER(ch);
 
-          if (ch == LF) {
-            CALLBACK(header_value);
-            goto header_almost_done;
-          }
+        if (ch == CR) {
+          CALLBACK(header_value);
+          state = s_header_almost_done;
           break;
         }
 
+        if (ch == LF) {
+          CALLBACK(header_value);
+          goto header_almost_done;
+        }
+
         switch (header_state) {
           case h_general:
             break;
@@ -1373,6 +1423,7 @@ size_t http_parser_execute (http_parser *parser,
               break;
 
             default:
+              parser->state = state;
               return p - data; /* Error */
           }
         }
@@ -1436,6 +1487,7 @@ size_t http_parser_execute (http_parser *parser,
 
       case s_chunk_size_start:
       {
+        assert(nread == 1);
         assert(parser->flags & F_CHUNKED);
 
         c = unhex[(unsigned char)ch];
@@ -1485,6 +1537,8 @@ size_t http_parser_execute (http_parser *parser,
         assert(parser->flags & F_CHUNKED);
         STRICT_CHECK(ch != LF);
 
+        nread = 0;
+
         if (parser->content_length == 0) {
           parser->flags |= F_TRAILING;
           state = s_header_field_start;