giraffesoft-unicorn 0.93.5

data/examples/echo.ru

@@ -0,0 +1,27 @@
+#\-E none
+#
+# Example application that echoes read data back to the HTTP client.
+# This emulates the old echo protocol people used to run.
+#
+# An example of using this in a client would be to run:
+#   curl --no-buffer -T- http://host:port/
+#
+# Then type random stuff in your terminal to watch it get echoed back!
+
+class EchoBody < Struct.new(:input)
+
+  def each(&block)
+    while buf = input.read(4096)
+      yield buf
+    end
+    self
+  end
+
+end
+
+use Rack::Chunked
+run lambda { |env|
+  /\A100-continue\z/i =~ env['HTTP_EXPECT'] and return [100, {}, []]
+  [ 200, { 'Content-Type' => 'application/octet-stream' },
+    EchoBody.new(env['rack.input']) ]
+}

data/examples/git.ru

@@ -0,0 +1,13 @@
+#\-E none
+
+# See http://thread.gmane.org/gmane.comp.web.curl.general/10473/raw on
+# how to setup git for this.  A better version of the above patch was
+# accepted and committed on June 15, 2009, so you can pull the latest
+# curl CVS snapshot to try this out.
+require 'unicorn/app/inetd'
+
+use Rack::Lint
+use Rack::Chunked # important!
+run Unicorn::App::Inetd.new(
+ *%w(git daemon --verbose --inetd --export-all --base-path=/home/ew/unicorn)
+)

data/examples/init.sh

@@ -0,0 +1,53 @@
+#!/bin/sh
+set -e
+# Example init script, this can be used with nginx, too,
+# since nginx and unicorn accept the same signals
+
+# Feel free to change any of the following variables for your app:
+APP_ROOT=/home/x/my_app/current
+PID=$APP_ROOT/tmp/pids/unicorn.pid
+CMD="/usr/bin/unicorn -D -c $APP_ROOT/config/unicorn.rb"
+INIT_CONF=$APP_ROOT/config/init.conf
+
+test -f "$INIT_CONF" && . $INIT_CONF
+
+old_pid="$PID.oldbin"
+
+cd $APP_ROOT || exit 1
+
+sig () {
+	test -s "$PID" && kill -$1 `cat $PID`
+}
+
+oldsig () {
+	test -s $old_pid && kill -$1 `cat $old_pid`
+}
+
+case $1 in
+start)
+	sig 0 && echo >&2 "Already running" && exit 0
+	$CMD
+	;;
+stop)
+	sig QUIT && exit 0
+	echo >&2 "Not running"
+	;;
+force-stop)
+	sig TERM && exit 0
+	echo >&2 "Not running"
+	;;
+restart|reload)
+	sig HUP && echo reloaded OK && exit 0
+	echo >&2 "Couldn't reload, starting '$CMD' instead"
+	$CMD
+	;;
+upgrade)
+	sig USR2 && sleep 2 && sig 0 && oldsig QUIT && exit 0
+	echo >&2 "Couldn't upgrade, starting '$CMD' instead"
+	$CMD
+	;;
+*)
+	echo >&2 "Usage: $0 <start|stop|restart|upgrade|force-stop>"
+	exit 1
+	;;
+esac

data/ext/unicorn_http/c_util.h

@@ -0,0 +1,107 @@
+/*
+ * Generic C functions and macros go here, there are no dependencies
+ * on Unicorn internal structures or the Ruby C API in here.
+ */
+
+#ifndef UH_util_h
+#define UH_util_h
+
+#include <unistd.h>
+#include <assert.h>
+
+#define MIN(a,b) (a < b ? a : b)
+#define ARRAY_SIZE(x) (sizeof(x)/sizeof(x[0]))
+
+#ifndef SIZEOF_OFF_T
+#  define SIZEOF_OFF_T 4
+#  warning SIZEOF_OFF_T not defined, guessing 4.  Did you run extconf.rb?
+#endif
+
+#if SIZEOF_OFF_T == 4
+#  define UH_OFF_T_MAX 0x7fffffff
+#elif SIZEOF_OFF_T == 8
+#  if SIZEOF_LONG == 4
+#    define UH_OFF_T_MAX 0x7fffffffffffffffLL
+#  else
+#    define UH_OFF_T_MAX 0x7fffffffffffffff
+#  endif
+#else
+#  error off_t size unknown for this platform!
+#endif /* SIZEOF_OFF_T check */
+
+/*
+ * capitalizes all lower-case ASCII characters and converts dashes
+ * to underscores for HTTP headers.  Locale-agnostic.
+ */
+static void snake_upcase_char(char *c)
+{
+  if (*c >= 'a' && *c <= 'z')
+    *c &= ~0x20;
+  else if (*c == '-')
+    *c = '_';
+}
+
+/* Downcases a single ASCII character.  Locale-agnostic. */
+static void downcase_char(char *c)
+{
+  if (*c >= 'A' && *c <= 'Z')
+    *c |= 0x20;
+}
+
+static int hexchar2int(int xdigit)
+{
+  if (xdigit >= 'A' && xdigit <= 'F')
+    return xdigit - 'A' + 10;
+  if (xdigit >= 'a' && xdigit <= 'f')
+    return xdigit - 'a' + 10;
+
+  /* Ragel already does runtime range checking for us in Unicorn: */
+  assert(xdigit >= '0' && xdigit <= '9' && "invalid digit character");
+
+  return xdigit - '0';
+}
+
+/*
+ * multiplies +i+ by +base+ and increments the result by the parsed
+ * integer value of +xdigit+.  +xdigit+ is a character byte
+ * representing a number the range of 0..(base-1)
+ * returns the new value of +i+ on success
+ * returns -1 on errors (including overflow)
+ */
+static off_t step_incr(off_t i, int xdigit, const int base)
+{
+  static const off_t max = UH_OFF_T_MAX;
+  const off_t next_max = (max - (max % base)) / base;
+  off_t offset = hexchar2int(xdigit);
+
+  if (offset > (base - 1))
+    return -1;
+  if (i > next_max)
+    return -1;
+  i *= base;
+
+  if ((offset > (base - 1)) || ((max - i) < offset))
+    return -1;
+
+  return i + offset;
+}
+
+/*
+ * parses a non-negative length according to base-10 and
+ * returns it as an off_t value.  Returns -1 on errors
+ * (including overflow).
+ */
+static off_t parse_length(const char *value, size_t length)
+{
+  off_t rv;
+
+  for (rv = 0; length-- && rv >= 0; ++value)
+    rv = step_incr(rv, *value, 10);
+
+  return rv;
+}
+
+#define CONST_MEM_EQ(const_p, buf, len) \
+  ((sizeof(const_p) - 1) == len && !memcmp(const_p, buf, sizeof(const_p) - 1))
+
+#endif /* UH_util_h */

data/ext/unicorn_http/common_field_optimization.h

@@ -0,0 +1,111 @@
+#ifndef common_field_optimization
+#define common_field_optimization
+#include "ruby.h"
+#include "c_util.h"
+
+struct common_field {
+  const signed long len;
+  const char *name;
+  VALUE value;
+};
+
+/*
+ * A list of common HTTP headers we expect to receive.
+ * This allows us to avoid repeatedly creating identical string
+ * objects to be used with rb_hash_aset().
+ */
+static struct common_field common_http_fields[] = {
+# define f(N) { (sizeof(N) - 1), N, Qnil }
+  f("ACCEPT"),
+  f("ACCEPT_CHARSET"),
+  f("ACCEPT_ENCODING"),
+  f("ACCEPT_LANGUAGE"),
+  f("ALLOW"),
+  f("AUTHORIZATION"),
+  f("CACHE_CONTROL"),
+  f("CONNECTION"),
+  f("CONTENT_ENCODING"),
+  f("CONTENT_LENGTH"),
+  f("CONTENT_TYPE"),
+  f("COOKIE"),
+  f("DATE"),
+  f("EXPECT"),
+  f("FROM"),
+  f("HOST"),
+  f("IF_MATCH"),
+  f("IF_MODIFIED_SINCE"),
+  f("IF_NONE_MATCH"),
+  f("IF_RANGE"),
+  f("IF_UNMODIFIED_SINCE"),
+  f("KEEP_ALIVE"), /* Firefox sends this */
+  f("MAX_FORWARDS"),
+  f("PRAGMA"),
+  f("PROXY_AUTHORIZATION"),
+  f("RANGE"),
+  f("REFERER"),
+  f("TE"),
+  f("TRAILER"),
+  f("TRANSFER_ENCODING"),
+  f("UPGRADE"),
+  f("USER_AGENT"),
+  f("VIA"),
+  f("X_FORWARDED_FOR"), /* common for proxies */
+  f("X_FORWARDED_PROTO"), /* common for proxies */
+  f("X_REAL_IP"), /* common for proxies */
+  f("WARNING")
+# undef f
+};
+
+#define HTTP_PREFIX "HTTP_"
+#define HTTP_PREFIX_LEN (sizeof(HTTP_PREFIX) - 1)
+
+/* this function is not performance-critical, called only at load time */
+static void init_common_fields(void)
+{
+  int i;
+  struct common_field *cf = common_http_fields;
+  char tmp[64];
+  memcpy(tmp, HTTP_PREFIX, HTTP_PREFIX_LEN);
+
+  for(i = 0; i < ARRAY_SIZE(common_http_fields); cf++, i++) {
+    /* Rack doesn't like certain headers prefixed with "HTTP_" */
+    if (!strcmp("CONTENT_LENGTH", cf->name) ||
+        !strcmp("CONTENT_TYPE", cf->name)) {
+      cf->value = rb_str_new(cf->name, cf->len);
+    } else {
+      memcpy(tmp + HTTP_PREFIX_LEN, cf->name, cf->len + 1);
+      cf->value = rb_str_new(tmp, HTTP_PREFIX_LEN + cf->len);
+    }
+    cf->value = rb_obj_freeze(cf->value);
+    rb_global_variable(&cf->value);
+  }
+}
+
+/* this function is called for every header set */
+static VALUE find_common_field(const char *field, size_t flen)
+{
+  int i;
+  struct common_field *cf = common_http_fields;
+
+  for(i = 0; i < ARRAY_SIZE(common_http_fields); i++, cf++) {
+    if (cf->len == flen && !memcmp(cf->name, field, flen))
+      return cf->value;
+  }
+  return Qnil;
+}
+
+/*
+ * We got a strange header that we don't have a memoized value for.
+ * Fallback to creating a new string to use as a hash key.
+ */
+static VALUE uncommon_field(const char *field, size_t flen)
+{
+  VALUE f = rb_str_new(NULL, HTTP_PREFIX_LEN + flen);
+  memcpy(RSTRING_PTR(f), HTTP_PREFIX, HTTP_PREFIX_LEN);
+  memcpy(RSTRING_PTR(f) + HTTP_PREFIX_LEN, field, flen);
+  assert(*(RSTRING_PTR(f) + RSTRING_LEN(f)) == '\0' &&
+         "string didn't end with \\0"); /* paranoia */
+  return rb_obj_freeze(f);
+}
+
+#endif /* common_field_optimization_h */

data/ext/unicorn_http/ext_help.h

@@ -0,0 +1,73 @@
+#ifndef ext_help_h
+#define ext_help_h
+
+#ifndef RSTRING_PTR
+#define RSTRING_PTR(s) (RSTRING(s)->ptr)
+#endif /* !defined(RSTRING_PTR) */
+#ifndef RSTRING_LEN
+#define RSTRING_LEN(s) (RSTRING(s)->len)
+#endif /* !defined(RSTRING_LEN) */
+
+#ifndef RUBINIUS
+#  define rb_str_update(x) do {} while (0)
+#  define rb_str_flush(x) do {} while (0)
+#endif /* !RUBINIUS */
+
+#ifndef HAVE_RB_STR_SET_LEN
+/* this is taken from Ruby 1.8.7, 1.8.6 may not have it */
+static void rb_18_str_set_len(VALUE str, long len)
+{
+  RSTRING(str)->len = len;
+  RSTRING(str)->ptr[len] = '\0';
+  rb_str_flush(str);
+}
+#  define rb_str_set_len(str,len) rb_18_str_set_len(str,len)
+#endif /* !defined(HAVE_RB_STR_SET_LEN) */
+
+/* not all Ruby implementations support frozen objects (Rubinius does not) */
+#if defined(OBJ_FROZEN)
+#  define assert_frozen(f) assert(OBJ_FROZEN(f) && "unfrozen object")
+#else
+#  define assert_frozen(f) do {} while (0)
+#endif /* !defined(OBJ_FROZEN) */
+
+#if !defined(OFFT2NUM)
+#  if SIZEOF_OFF_T == SIZEOF_LONG
+#    define OFFT2NUM(n) LONG2NUM(n)
+#  else
+#    define OFFT2NUM(n) LL2NUM(n)
+#  endif
+#endif /* ! defined(OFFT2NUM) */
+
+#ifndef HAVE_RB_STR_MODIFY
+#  define rb_str_modify(x) do {} while (0)
+#endif /* ! defined(HAVE_RB_STR_MODIFY) */
+
+static inline int str_cstr_eq(VALUE val, const char *ptr, size_t len)
+{
+  return (RSTRING_LEN(val) == len && !memcmp(ptr, RSTRING_PTR(val), len));
+}
+
+#define STR_CSTR_EQ(val, const_str) \
+  str_cstr_eq(val, const_str, sizeof(const_str) - 1)
+
+/* strcasecmp isn't locale independent */
+static int str_cstr_case_eq(VALUE val, const char *ptr, size_t len)
+{
+  if (RSTRING_LEN(val) == len) {
+    const char *v = RSTRING_PTR(val);
+
+    for (; len--; ++ptr, ++v) {
+      if ((*ptr == *v) || (*v >= 'A' && *v <= 'Z' && (*v | 0x20) == *ptr))
+        continue;
+      return 0;
+    }
+    return 1;
+  }
+  return 0;
+}
+
+#define STR_CSTR_CASE_EQ(val, const_str) \
+  str_cstr_case_eq(val, const_str, sizeof(const_str) - 1)
+
+#endif /* ext_help_h */

data/ext/unicorn_http/extconf.rb

@@ -0,0 +1,14 @@
+# -*- encoding: binary -*-
+require 'mkmf'
+
+dir_config("unicorn_http")
+
+have_macro("SIZEOF_OFF_T", "ruby.h") or check_sizeof("off_t", "sys/types.h")
+have_macro("SIZEOF_LONG", "ruby.h") or check_sizeof("long", "sys/types.h")
+have_func("rb_str_set_len", "ruby.h")
+have_func("rb_str_modify", "ruby.h")
+
+# -fPIC is needed for Rubinius, MRI already uses it regardless
+with_cflags($CFLAGS + " -fPIC ") do
+  create_makefile("unicorn_http")
+end

data/ext/unicorn_http/global_variables.h

@@ -0,0 +1,91 @@
+#ifndef global_variables_h
+#define global_variables_h
+static VALUE mUnicorn;
+static VALUE cHttpParser;
+static VALUE eHttpParserError;
+
+static VALUE g_rack_url_scheme;
+static VALUE g_request_method;
+static VALUE g_request_uri;
+static VALUE g_fragment;
+static VALUE g_query_string;
+static VALUE g_http_version;
+static VALUE g_request_path;
+static VALUE g_path_info;
+static VALUE g_server_name;
+static VALUE g_server_port;
+static VALUE g_server_protocol;
+static VALUE g_http_host;
+static VALUE g_http_x_forwarded_proto;
+static VALUE g_http_transfer_encoding;
+static VALUE g_content_length;
+static VALUE g_http_trailer;
+static VALUE g_http_connection;
+static VALUE g_port_80;
+static VALUE g_port_443;
+static VALUE g_localhost;
+static VALUE g_http;
+static VALUE g_http_09;
+static VALUE g_http_10;
+static VALUE g_http_11;
+static VALUE g_GET;
+static VALUE g_HEAD;
+
+/** Defines common length and error messages for input length validation. */
+#define DEF_MAX_LENGTH(N, length) \
+  static const size_t MAX_##N##_LENGTH = length; \
+  static const char * const MAX_##N##_LENGTH_ERR = \
+    "HTTP element " # N  " is longer than the " # length " allowed length."
+
+/**
+ * Validates the max length of given input and throws an HttpParserError
+ * exception if over.
+ */
+#define VALIDATE_MAX_LENGTH(len, N) do { \
+  if (len > MAX_##N##_LENGTH) \
+    rb_raise(eHttpParserError, MAX_##N##_LENGTH_ERR); \
+} while (0)
+
+/** Defines global strings in the init method. */
+#define DEF_GLOBAL(N, val) do { \
+  g_##N = rb_obj_freeze(rb_str_new(val, sizeof(val) - 1)); \
+  rb_global_variable(&g_##N); \
+} while (0)
+
+/* Defines the maximum allowed lengths for various input elements.*/
+DEF_MAX_LENGTH(FIELD_NAME, 256);
+DEF_MAX_LENGTH(FIELD_VALUE, 80 * 1024);
+DEF_MAX_LENGTH(REQUEST_URI, 1024 * 12);
+DEF_MAX_LENGTH(FRAGMENT, 1024); /* Don't know if this length is specified somewhere or not */
+DEF_MAX_LENGTH(REQUEST_PATH, 1024);
+DEF_MAX_LENGTH(QUERY_STRING, (1024 * 10));
+DEF_MAX_LENGTH(HEADER, (1024 * (80 + 32)));
+
+void init_globals(void)
+{
+  DEF_GLOBAL(rack_url_scheme, "rack.url_scheme");
+  DEF_GLOBAL(request_method, "REQUEST_METHOD");
+  DEF_GLOBAL(request_uri, "REQUEST_URI");
+  DEF_GLOBAL(fragment, "FRAGMENT");
+  DEF_GLOBAL(query_string, "QUERY_STRING");
+  DEF_GLOBAL(http_version, "HTTP_VERSION");
+  DEF_GLOBAL(request_path, "REQUEST_PATH");
+  DEF_GLOBAL(path_info, "PATH_INFO");
+  DEF_GLOBAL(server_name, "SERVER_NAME");
+  DEF_GLOBAL(server_port, "SERVER_PORT");
+  DEF_GLOBAL(server_protocol, "SERVER_PROTOCOL");
+  DEF_GLOBAL(http_x_forwarded_proto, "HTTP_X_FORWARDED_PROTO");
+  DEF_GLOBAL(port_80, "80");
+  DEF_GLOBAL(port_443, "443");
+  DEF_GLOBAL(localhost, "localhost");
+  DEF_GLOBAL(http, "http");
+  DEF_GLOBAL(http_11, "HTTP/1.1");
+  DEF_GLOBAL(http_10, "HTTP/1.0");
+  DEF_GLOBAL(http_09, "HTTP/0.9");
+  DEF_GLOBAL(GET, "GET");
+  DEF_GLOBAL(HEAD, "HEAD");
+}
+
+#undef DEF_GLOBAL
+
+#endif /* global_variables_h */