json_pure 1.0.0

data/ext/json/ext/parser/unicode.c

@@ -0,0 +1,156 @@
+/* vim: set cin et sw=4 ts=4: */
+
+#include "unicode.h"
+
+/*
+ * Copyright 2001-2004 Unicode, Inc.
+ * 
+ * Disclaimer
+ * 
+ * This source code is provided as is by Unicode, Inc. No claims are
+ * made as to fitness for any particular purpose. No warranties of any
+ * kind are expressed or implied. The recipient agrees to determine
+ * applicability of information provided. If this file has been
+ * purchased on magnetic or optical media from Unicode, Inc., the
+ * sole remedy for any claim will be exchange of defective media
+ * within 90 days of receipt.
+ * 
+ * Limitations on Rights to Redistribute This Code
+ * 
+ * Unicode, Inc. hereby grants the right to freely use the information
+ * supplied in this file in the creation of products supporting the
+ * Unicode Standard, and to make copies of this file in any form
+ * for internal or external distribution as long as this notice
+ * remains attached.
+ */
+
+/*
+ * Index into the table below with the first byte of a UTF-8 sequence to
+ * get the number of trailing bytes that are supposed to follow it.
+ * Note that *legal* UTF-8 values can't have 4 or 5-bytes. The table is
+ * left as-is for anyone who may want to do such conversion, which was
+ * allowed in earlier algorithms.
+ */
+static const char trailingBytesForUTF8[256] = {
+    0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
+    0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
+    0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
+    0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
+    0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
+    0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
+    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,
+    2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, 3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5
+};
+
+/*
+ * Magic values subtracted from a buffer value during UTF8 conversion.
+ * This table contains as many values as there might be trailing bytes
+ * in a UTF-8 sequence.
+ */
+static const UTF32 offsetsFromUTF8[6] = { 0x00000000UL, 0x00003080UL, 0x000E2080UL, 
+             0x03C82080UL, 0xFA082080UL, 0x82082080UL };
+
+/*
+ * Once the bits are split out into bytes of UTF-8, this is a mask OR-ed
+ * into the first byte, depending on how many bytes follow.  There are
+ * as many entries in this table as there are UTF-8 sequence types.
+ * (I.e., one byte sequence, two byte... etc.). Remember that sequencs
+ * for *legal* UTF-8 will be 4 or fewer bytes total.
+ */
+static const UTF8 firstByteMark[7] = { 0x00, 0x00, 0xC0, 0xE0, 0xF0, 0xF8, 0xFC };
+
+inline char *JSON_convert_UTF16_to_UTF8 (
+        VALUE buffer,
+        char *source,
+        char *sourceEnd,
+        ConversionFlags flags)
+{
+    UTF16 *tmp, *tmpPtr, *tmpEnd;
+    char buf[5];
+    long n = 0, i;
+    char *p = source - 1;
+
+    while (p < sourceEnd && p[0] == '\\' && p[1] == 'u') {
+        p += 6;
+        n++;
+    }
+    p = source + 1;
+    buf[4] = 0;
+    tmpPtr = tmp = ALLOC_N(UTF16, n);
+    tmpEnd = tmp + n;
+    for (i = 0; i < n; i++) {
+        buf[0] = *p++;
+        buf[1] = *p++;
+        buf[2] = *p++;
+        buf[3] = *p++;
+        tmpPtr[i] = strtol(buf, NULL, 16);
+        p += 2;
+    }
+
+    while (tmpPtr < tmpEnd) {
+        UTF32 ch;
+        unsigned short bytesToWrite = 0;
+        const UTF32 byteMask = 0xBF;
+        const UTF32 byteMark = 0x80; 
+        ch = *tmpPtr++;
+        /* If we have a surrogate pair, convert to UTF32 first. */
+        if (ch >= UNI_SUR_HIGH_START && ch <= UNI_SUR_HIGH_END) {
+            /* If the 16 bits following the high surrogate are in the source
+             * buffer... */
+            if (tmpPtr < tmpEnd) {
+                UTF32 ch2 = *tmpPtr;
+                /* If it's a low surrogate, convert to UTF32. */
+                if (ch2 >= UNI_SUR_LOW_START && ch2 <= UNI_SUR_LOW_END) {
+                    ch = ((ch - UNI_SUR_HIGH_START) << halfShift)
+                        + (ch2 - UNI_SUR_LOW_START) + halfBase;
+                    ++tmpPtr;
+                } else if (flags == strictConversion) { /* it's an unpaired high surrogate */
+                    free(tmp);
+                    rb_raise(rb_path2class("JSON::ParserError"),
+                            "source sequence is illegal/malformed near %s", source);
+                }
+            } else { /* We don't have the 16 bits following the high surrogate. */
+                free(tmp);
+                rb_raise(rb_path2class("JSON::ParserError"),
+                    "partial character in source, but hit end near %s", source);
+                break;
+            }
+        } else if (flags == strictConversion) {
+            /* UTF-16 surrogate values are illegal in UTF-32 */
+            if (ch >= UNI_SUR_LOW_START && ch <= UNI_SUR_LOW_END) {
+                free(tmp);
+                rb_raise(rb_path2class("JSON::ParserError"),
+                    "source sequence is illegal/malformed near %s", source);
+            }
+        }
+        /* Figure out how many bytes the result will require */
+        if (ch < (UTF32) 0x80) {
+            bytesToWrite = 1;
+        } else if (ch < (UTF32) 0x800) {
+            bytesToWrite = 2;
+        } else if (ch < (UTF32) 0x10000) {
+            bytesToWrite = 3;
+        } else if (ch < (UTF32) 0x110000) {
+            bytesToWrite = 4;
+        } else {
+            bytesToWrite = 3;
+            ch = UNI_REPLACEMENT_CHAR;
+        }
+
+        buf[0] = 0;
+        buf[1] = 0;
+        buf[2] = 0;
+        buf[3] = 0;
+        p = buf + bytesToWrite;
+        switch (bytesToWrite) { /* note: everything falls through. */
+            case 4: *--p = (UTF8) ((ch | byteMark) & byteMask); ch >>= 6;
+            case 3: *--p = (UTF8) ((ch | byteMark) & byteMask); ch >>= 6;
+            case 2: *--p = (UTF8) ((ch | byteMark) & byteMask); ch >>= 6;
+            case 1: *--p = (UTF8) (ch | firstByteMark[bytesToWrite]);
+        }
+        rb_str_buf_cat(buffer, p, bytesToWrite);
+    }
+    free(tmp);
+    source += 5 + (n - 1) * 6;
+    return source;
+}

data/ext/json/ext/parser/unicode.h

@@ -0,0 +1,44 @@
+
+#ifndef _PARSER_UNICODE_H_
+#define _PARSER_UNICODE_H_
+
+#include "ruby.h"
+
+typedef unsigned long	UTF32;	/* at least 32 bits */
+typedef unsigned short	UTF16;	/* at least 16 bits */
+typedef unsigned char	UTF8;	/* typically 8 bits */
+
+#define UNI_REPLACEMENT_CHAR (UTF32)0x0000FFFD
+#define UNI_MAX_BMP (UTF32)0x0000FFFF
+#define UNI_MAX_UTF16 (UTF32)0x0010FFFF
+#define UNI_MAX_UTF32 (UTF32)0x7FFFFFFF
+#define UNI_MAX_LEGAL_UTF32 (UTF32)0x0010FFFF
+
+#define UNI_SUR_HIGH_START  (UTF32)0xD800
+#define UNI_SUR_HIGH_END    (UTF32)0xDBFF
+#define UNI_SUR_LOW_START   (UTF32)0xDC00
+#define UNI_SUR_LOW_END     (UTF32)0xDFFF
+
+static const int halfShift  = 10; /* used for shifting by 10 bits */
+
+static const UTF32 halfBase = 0x0010000UL;
+static const UTF32 halfMask = 0x3FFUL;
+
+typedef enum {
+	conversionOK = 0, 	/* conversion successful */
+	sourceExhausted,	/* partial character in source, but hit end */
+	targetExhausted,	/* insuff. room in target for conversion */
+	sourceIllegal		/* source sequence is illegal/malformed */
+} ConversionResult;
+
+typedef enum {
+	strictConversion = 0,
+	lenientConversion
+} ConversionFlags;
+
+char *JSON_convert_UTF16_to_UTF8 (
+    VALUE buffer,
+    char *source,
+    char *sourceEnd,
+		ConversionFlags flags);
+#endif

data/install.rb

@@ -0,0 +1,26 @@
+#!/usr/bin/env ruby
+
+require 'rbconfig'
+require 'fileutils'
+include FileUtils::Verbose
+
+include Config
+
+bindir = CONFIG["bindir"]
+cd 'bin' do
+  filename = 'edit_json.rb'
+  #install(filename, bindir)
+end
+sitelibdir = CONFIG["sitelibdir"]
+cd 'lib' do
+  install('json.rb', sitelibdir)
+  mkdir_p File.join(sitelibdir, 'json')
+  for file in Dir['json/**/*.{rb,xpm}']
+    d = File.join(sitelibdir, file)
+    mkdir_p File.dirname(d)
+    install(file, d)
+  end
+  install(File.join('json', 'editor.rb'), File.join(sitelibdir,'json'))
+  install(File.join('json', 'json.xpm'), File.join(sitelibdir,'json'))
+end
+warn " *** Installed PURE ruby library."

data/lib/json.rb

@@ -0,0 +1,205 @@
+require 'json/common'
+# = json - JSON for Ruby
+#
+# == Description
+#
+# This is a implementation of the JSON specification according to RFC 4627
+# (http://www.ietf.org/rfc/rfc4627.txt). Starting from version 1.0.0 on there
+# will be two variants available:
+#
+# * A pure ruby variant, that relies on the iconv and the stringscan
+#   extensions, which are both part of the ruby standard library.
+# * The quite a bit faster C extension variant, which is in parts implemented
+#   in C and comes with its own unicode conversion functions and a parser
+#   generated by the ragel state machine compiler
+#   (http://www.cs.queensu.ca/~thurston/ragel).
+#
+# Both variants of the JSON generator escape all non-ASCII an control
+# characters with \uXXXX escape sequences, and support UTF-16 surrogate pairs
+# in order to be able to generate the whole range of unicode code points. This
+# means that generated JSON text is encoded as UTF-8 (because ASCII is a subset
+# of UTF-8) and at the same time avoids decoding problems for receiving
+# endpoints, that don't expect UTF-8 encoded texts. On the negative side this
+# may lead to a bit longer strings than necessarry.
+#
+# All strings, that are to be encoded as JSON strings, should be UTF-8 byte
+# sequences on the Ruby side. To encode raw binary strings, that aren't UTF-8
+# encoded, please use the to_json_raw_object method of String (which produces
+# an object, that contains a byte array) and decode the result on the receiving
+# endpoint.
+#
+# == Author
+#
+# Florian Frank <mailto:flori@ping.de>
+#
+# == License
+#
+# This is free software; you can redistribute it and/or modify it under the
+# terms of the GNU General Public License Version 2 as published by the Free
+# Software Foundation: www.gnu.org/copyleft/gpl.html
+#
+# == Download
+#
+# The latest version of this library can be downloaded at
+#
+# * http://rubyforge.org/frs?group_id=953
+#
+# Online Documentation should be located at
+#
+# * http://json.rubyforge.org
+#
+# == Speed Comparisons
+#
+# I have created some benchmark results (see the benchmarks subdir of the
+# package) for the JSON-Parser to estimate the speed up in the C extension:
+#
+# JSON::Pure::Parser::  28.90  calls/second
+# JSON::Ext::Parser::  505.50 calls/second
+#
+# This is ca. <b>17.5</b> times the speed of the pure Ruby implementation.
+#
+# I have benchmarked the JSON-Generator as well. This generates a few more
+# values, because there are different modes, that also influence the achieved
+# speed:
+#
+# * JSON::Pure::Generator:
+#   generate::        35.06 calls/second
+#   pretty_generate:: 34.00 calls/second
+#   fast_generate::   41.06 calls/second
+#
+# * JSON::Ext::Generator:
+#   generate::        492.11 calls/second
+#   pretty_generate:: 348.85 calls/second
+#   fast_generate::   541.60 calls/second
+#
+# * Speedup Ext/Pure:
+#   generate safe::   14.0 times
+#   generate pretty:: 10.3 times
+#   generate fast::   13.2 times
+#
+# The rails framework includes a generator as well, also it seems to be rather
+# slow: I measured only 23.87 calls/second which is slower than any of my pure
+# generator results. Here a comparison of the different speedups with the Rails
+# measurement as the divisor:
+#
+# * Speedup Pure/Rails:
+#   generate safe::   1.5 times
+#   generate pretty:: 1.4 times
+#   generate fast::   1.7 times
+#
+# * Speedup Ext/Rails:
+#   generate safe::   20.6 times
+#   generate pretty:: 14.6 times
+#   generate fast::   22.7 times
+#
+# To achieve the fastest JSON text output, you can use the
+# fast_generate/fast_unparse methods. Beware, that this will disable the
+# checking for circular Ruby data structures, which may cause JSON to go into
+# an infinite loop.
+#
+# == Examples
+#
+# To create a JSON text from a ruby data structure, you
+# can call JSON.generate (or JSON.unparse) like that:
+#
+#  json = JSON.generate [1, 2, {"a"=>3.141}, false, true, nil, 4..10]
+#  # => "[1,2,{\"a\":3.141},false,true,null,\"4..10\"]"
+#
+# It's also possible to call the #to_json method directly.
+#
+#  json = [1, 2, {"a"=>3.141}, false, true, nil, 4..10].to_json
+#  # => "[1,2,{\"a\":3.141},false,true,null,\"4..10\"]"
+#
+# To create a valid JSON text you have to make sure, that the output is
+# embedded in either a JSON array [] or a JSON object {}. The easiest way to do
+# this, is by putting your values in a Ruby Array or Hash instance.
+#
+# To get back a ruby data structure from a JSON text, you have to call
+# JSON.parse on it:
+#
+#  JSON.parse json
+#  # => [1, 2, {"a"=>3.141}, false, true, nil, "4..10"]
+# 
+# Note, that the range from the original data structure is a simple
+# string now. The reason for this is, that JSON doesn't support ranges
+# or arbitrary classes. In this case the json library falls back to call
+# Object#to_json, which is the same as #to_s.to_json.
+#
+# It's possible to extend JSON to support serialization of arbitrary classes by
+# simply implementing a more specialized version of the #to_json method, that
+# should return a JSON object (a hash converted to JSON with #to_json)
+# like this (don't forget the *a for all the arguments):
+#
+#  class Range
+#    def to_json(*a)
+#      {
+#        'json_class'   => self.class.name, # = 'Range'
+#        'data'         => [ first, last, exclude_end? ]
+#      }.to_json(*a)
+#    end
+#  end
+#
+# The hash key 'json_class' is the class, that will be asked to deserialize the
+# JSON representation later. In this case it's 'Range', but any namespace of
+# the form 'A::B' or '::A::B' will do. All other keys are arbitrary and can be
+# used to store the necessary data to configure the object to be deserialized.
+#
+# If a the key 'json_class' is found in a JSON object, the JSON parser checks
+# if the given class responds to the json_create class method. If so, it is
+# called with the JSON object converted to a Ruby hash. So a range can
+# be deserialized by implementing Range.json_create like this:
+# 
+#  class Range
+#    def self.json_create(o)
+#      new(*o['data'])
+#    end
+#  end
+#
+# Now it possible to serialize/deserialize ranges as well:
+#
+#  json = JSON.generate [1, 2, {"a"=>3.141}, false, true, nil, 4..10]
+#  # => "[1,2,{\"a\":3.141},false,true,null,{\"json_class\":\"Range\",\"data\":[4,10,false]}]"
+#  JSON.parse json
+#  # => [1, 2, {"a"=>3.141}, false, true, nil, 4..10]
+#
+# JSON.generate always creates the shortest possible string representation of a
+# ruby data structure in one line. This good for data storage or network
+# protocols, but not so good for humans to read. Fortunately there's also
+# JSON.pretty_generate (or JSON.pretty_generate) that creates a more
+# readable output:
+#
+#  puts JSON.pretty_generate([1, 2, {"a"=>3.141}, false, true, nil, 4..10])
+#  [
+#    1,
+#    2,
+#    {
+#      "a": 3.141
+#    },
+#    false,
+#    true,
+#    null,
+#    {
+#      "json_class": "Range",
+#      "data": [
+#        4,
+#        10,
+#        false
+#      ]
+#    }
+#  ]
+#
+# There are also the methods Kernel#j for unparse, and Kernel#jj for
+# pretty_unparse output to the console, that work analogous to Core Ruby's p
+# and the pp library's pp methods.
+#
+# The script tools/server.rb contains a small example if you want to test, how
+# receiving a JSON object from a webrick server in your browser with the
+# javasript prototype library (http://www.prototypejs.org) works.
+#
+module JSON
+  begin
+    require 'json/ext'
+  rescue LoadError
+    require 'json/pure'
+  end
+end

data/lib/json/Array.xpm

@@ -0,0 +1,21 @@
+/* XPM */
+static char * Array_xpm[] = {
+"16 16 2 1",
+" 	c None",
+".	c #000000",
+"                ",
+"                ",
+"                ",
+"   ..........   ",
+"   .        .   ",
+"   .        .   ",
+"   .        .   ",
+"   .        .   ",
+"   .        .   ",
+"   .        .   ",
+"   .        .   ",
+"   .        .   ",
+"   ..........   ",
+"                ",
+"                ",
+"                "};