json 1.2.4 → 1.4.0

data/ext/json/ext/generator/unicode.c

@@ -1,180 +0,0 @@
-#include "unicode.h"
-
-#define unicode_escape(buffer, character)          \
-    snprintf(buf, 7, "\\u%04x", (unsigned int) (character)); \
-         rb_str_buf_cat(buffer, buf, 6);
-
-/*
- * 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 };
-
-/*
- * Utility routine to tell whether a sequence of bytes is legal UTF-8.
- * This must be called with the length pre-determined by the first byte.
- * If not calling this from ConvertUTF8to*, then the length can be set by:
- *  length = trailingBytesForUTF8[*source]+1;
- * and the sequence is illegal right away if there aren't that many bytes
- * available.
- * If presented with a length > 4, this returns 0.  The Unicode
- * definition of UTF-8 goes up to 4-byte sequences.
- */
-
-inline static unsigned char isLegalUTF8(const UTF8 *source, int length)
-{
-    UTF8 a;
-    const UTF8 *srcptr = source+length;
-    switch (length) {
-        default: return 0;
-                 /* Everything else falls through when "1"... */
-        case 4: if ((a = (*--srcptr)) < 0x80 || a > 0xBF) return 0;
-        case 3: if ((a = (*--srcptr)) < 0x80 || a > 0xBF) return 0;
-        case 2: if ((a = (*--srcptr)) > 0xBF) return 0;
-
-                    switch (*source) {
-                        /* no fall-through in this inner switch */
-                        case 0xE0: if (a < 0xA0) return 0; break;
-                        case 0xED: if (a > 0x9F) return 0; break;
-                        case 0xF0: if (a < 0x90) return 0; break;
-                        case 0xF4: if (a > 0x8F) return 0; break;
-                        default:   if (a < 0x80) return 0;
-                    }
-
-        case 1: if (*source >= 0x80 && *source < 0xC2) return 0;
-    }
-    if (*source > 0xF4) return 0;
-    return 1;
-}
-
-void JSON_convert_UTF8_to_JSON(VALUE buffer, VALUE string, ConversionFlags flags)
-{
-    char buf[7];
-    const UTF8* source = (UTF8 *) RSTRING_PTR(string);
-    const UTF8* sourceEnd = source + RSTRING_LEN(string);
-
-    while (source < sourceEnd) {
-        UTF32 ch = 0;
-        unsigned short extraBytesToRead = trailingBytesForUTF8[*source];
-        if (source + extraBytesToRead >= sourceEnd) {
-            rb_raise(rb_path2class("JSON::GeneratorError"),
-                    "partial character in source, but hit end");
-        }
-        if (!isLegalUTF8(source, extraBytesToRead+1)) {
-            rb_raise(rb_path2class("JSON::GeneratorError"),
-                    "source sequence is illegal/malformed utf-8");
-        }
-        /*
-         * The cases all fall through. See "Note A" below.
-         */
-        switch (extraBytesToRead) {
-            case 5: ch += *source++; ch <<= 6; /* remember, illegal UTF-8 */
-            case 4: ch += *source++; ch <<= 6; /* remember, illegal UTF-8 */
-            case 3: ch += *source++; ch <<= 6;
-            case 2: ch += *source++; ch <<= 6;
-            case 1: ch += *source++; ch <<= 6;
-            case 0: ch += *source++;
-        }
-        ch -= offsetsFromUTF8[extraBytesToRead];
-
-        if (ch <= UNI_MAX_BMP) { /* Target is a character <= 0xFFFF */
-            /* UTF-16 surrogate values are illegal in UTF-32 */
-            if (ch >= UNI_SUR_HIGH_START && ch <= UNI_SUR_LOW_END) {
-                if (flags == strictConversion) {
-                    source -= (extraBytesToRead+1); /* return to the illegal value itself */
-                    rb_raise(rb_path2class("JSON::GeneratorError"),
-                        "source sequence is illegal/malformed utf-8");
-                } else {
-                    unicode_escape(buffer, UNI_REPLACEMENT_CHAR);
-                }
-            } else {
-                /* normal case */
-                if (ch == '"') {
-                    rb_str_buf_cat2(buffer, "\\\"");
-                } else if (ch == '\\') {
-                    rb_str_buf_cat2(buffer, "\\\\");
-                } else if (ch >= 0x20 && ch <= 0x7f) {
-                    rb_str_buf_cat(buffer, (char *) source - 1, 1);
-                } else if (ch == '\n') {
-                    rb_str_buf_cat2(buffer, "\\n");
-                } else if (ch == '\r') {
-                    rb_str_buf_cat2(buffer, "\\r");
-                } else if (ch == '\t') {
-                    rb_str_buf_cat2(buffer, "\\t");
-                } else if (ch == '\f') {
-                    rb_str_buf_cat2(buffer, "\\f");
-                } else if (ch == '\b') {
-                    rb_str_buf_cat2(buffer, "\\b");
-                } else if (ch < 0x20) {
-                    unicode_escape(buffer, (UTF16) ch);
-                } else {
-                    unicode_escape(buffer, (UTF16) ch);
-                }
-            }
-        } else if (ch > UNI_MAX_UTF16) {
-            if (flags == strictConversion) {
-                source -= (extraBytesToRead+1); /* return to the start */
-                rb_raise(rb_path2class("JSON::GeneratorError"),
-                        "source sequence is illegal/malformed utf8");
-            } else {
-                unicode_escape(buffer, UNI_REPLACEMENT_CHAR);
-            }
-        } else {
-            /* target is a character in range 0xFFFF - 0x10FFFF. */
-            ch -= halfBase;
-            unicode_escape(buffer, (UTF16)((ch >> halfShift) + UNI_SUR_HIGH_START));
-            unicode_escape(buffer, (UTF16)((ch & halfMask) + UNI_SUR_LOW_START));
-        }
-    }
-}

data/ext/json/ext/generator/unicode.h

@@ -1,53 +0,0 @@
-#include "ruby.h"
-
-#ifndef _GENERATOR_UNICODE_H_
-#define _GENERATOR_UNICODE_H_
-
-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;
-
-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;
-
-void JSON_convert_UTF8_to_JSON(VALUE buffer, VALUE string, ConversionFlags flags);
-
-#ifndef RARRAY_PTR
-#define RARRAY_PTR(ARRAY) RARRAY(ARRAY)->ptr
-#endif
-#ifndef RARRAY_LEN
-#define RARRAY_LEN(ARRAY) RARRAY(ARRAY)->len
-#endif
-#ifndef RSTRING_PTR
-#define RSTRING_PTR(string) RSTRING(string)->ptr
-#endif
-#ifndef RSTRING_LEN
-#define RSTRING_LEN(string) RSTRING(string)->len
-#endif
-
-#endif

data/ext/json/ext/parser/extconf.rb

@@ -1,11 +0,0 @@
-require 'mkmf'
-require 'rbconfig'
-
-if CONFIG['CC'] =~ /gcc/
-  $CFLAGS += ' -Wall'
-  #$CFLAGS += ' -O0 -ggdb'
-end
-
-have_header("ruby/st.h") || have_header("st.h")
-have_header("re.h")
-create_makefile 'parser'

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

@@ -1,154 +0,0 @@
-#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 };
-
-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] = (UTF16)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 */
-                    ruby_xfree(tmp);
-                    rb_raise(rb_path2class("JSON::ParserError"),
-                            "\\uXXXX is illegal/malformed utf-16 near %s", source);
-                }
-            } else { /* We don't have the 16 bits following the high surrogate. */
-                ruby_xfree(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) {
-                ruby_xfree(tmp);
-                rb_raise(rb_path2class("JSON::ParserError"),
-                    "\\uXXXX is illegal/malformed utf-16 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);
-    }
-    ruby_xfree(tmp);
-    source += 5 + (n - 1) * 6;
-    return source;
-}

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

@@ -1,58 +0,0 @@
-
-#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);
-
-#ifndef RARRAY_PTR
-#define RARRAY_PTR(ARRAY) RARRAY(ARRAY)->ptr
-#endif
-#ifndef RARRAY_LEN
-#define RARRAY_LEN(ARRAY) RARRAY(ARRAY)->len
-#endif
-#ifndef RSTRING_PTR
-#define RSTRING_PTR(string) RSTRING(string)->ptr
-#endif
-#ifndef RSTRING_LEN
-#define RSTRING_LEN(string) RSTRING(string)->len
-#endif
-
-#endif