Wed, 31 Dec 2014 06:09:35 +0100
Cloned upstream origin tor-browser at tor-browser-31.3.0esr-4.5-1-build1
revision ID fc1c9ff7c1b2defdbc039f12214767608f46423f for hacking purpose.
michael@0 | 1 | /* |
michael@0 | 2 | ******************************************************************************* |
michael@0 | 3 | * |
michael@0 | 4 | * Copyright (C) 1998-2008, International Business Machines |
michael@0 | 5 | * Corporation and others. All Rights Reserved. |
michael@0 | 6 | * |
michael@0 | 7 | ******************************************************************************* |
michael@0 | 8 | * |
michael@0 | 9 | * File ucbuf.c |
michael@0 | 10 | * |
michael@0 | 11 | * Modification History: |
michael@0 | 12 | * |
michael@0 | 13 | * Date Name Description |
michael@0 | 14 | * 05/10/01 Ram Creation. |
michael@0 | 15 | * |
michael@0 | 16 | * This API reads in files and returns UChars |
michael@0 | 17 | ******************************************************************************* |
michael@0 | 18 | */ |
michael@0 | 19 | |
michael@0 | 20 | #include "unicode/ucnv.h" |
michael@0 | 21 | #include "filestrm.h" |
michael@0 | 22 | |
michael@0 | 23 | #if !UCONFIG_NO_CONVERSION |
michael@0 | 24 | |
michael@0 | 25 | #ifndef UCBUF_H |
michael@0 | 26 | #define UCBUF_H 1 |
michael@0 | 27 | |
michael@0 | 28 | typedef struct UCHARBUF UCHARBUF; |
michael@0 | 29 | /** |
michael@0 | 30 | * End of file value |
michael@0 | 31 | */ |
michael@0 | 32 | #define U_EOF 0xFFFFFFFF |
michael@0 | 33 | /** |
michael@0 | 34 | * Error value if a sequence cannot be unescaped |
michael@0 | 35 | */ |
michael@0 | 36 | #define U_ERR 0xFFFFFFFE |
michael@0 | 37 | |
michael@0 | 38 | typedef struct ULine ULine; |
michael@0 | 39 | |
michael@0 | 40 | struct ULine { |
michael@0 | 41 | UChar *name; |
michael@0 | 42 | int32_t len; |
michael@0 | 43 | }; |
michael@0 | 44 | |
michael@0 | 45 | /** |
michael@0 | 46 | * Opens the UCHARBUF with the given file stream and code page for conversion |
michael@0 | 47 | * @param fileName Name of the file to open. |
michael@0 | 48 | * @param codepage The encoding of the file stream to convert to Unicode. |
michael@0 | 49 | * If *codepoge is NULL on input the API will try to autodetect |
michael@0 | 50 | * popular Unicode encodings |
michael@0 | 51 | * @param showWarning Flag to print out warnings to STDOUT |
michael@0 | 52 | * @param buffered If TRUE performs a buffered read of the input file. If FALSE reads |
michael@0 | 53 | * the whole file into memory and converts it. |
michael@0 | 54 | * @param err is a pointer to a valid <code>UErrorCode</code> value. If this value |
michael@0 | 55 | * indicates a failure on entry, the function will immediately return. |
michael@0 | 56 | * On exit the value will indicate the success of the operation. |
michael@0 | 57 | * @return pointer to the newly opened UCHARBUF |
michael@0 | 58 | */ |
michael@0 | 59 | U_CAPI UCHARBUF* U_EXPORT2 |
michael@0 | 60 | ucbuf_open(const char* fileName,const char** codepage,UBool showWarning, UBool buffered, UErrorCode* err); |
michael@0 | 61 | |
michael@0 | 62 | /** |
michael@0 | 63 | * Gets a UTF-16 code unit at the current position from the converted buffer |
michael@0 | 64 | * and increments the current position |
michael@0 | 65 | * @param buf Pointer to UCHARBUF structure |
michael@0 | 66 | * @param err is a pointer to a valid <code>UErrorCode</code> value. If this value |
michael@0 | 67 | * indicates a failure on entry, the function will immediately return. |
michael@0 | 68 | * On exit the value will indicate the success of the operation. |
michael@0 | 69 | */ |
michael@0 | 70 | U_CAPI int32_t U_EXPORT2 |
michael@0 | 71 | ucbuf_getc(UCHARBUF* buf,UErrorCode* err); |
michael@0 | 72 | |
michael@0 | 73 | /** |
michael@0 | 74 | * Gets a UTF-32 code point at the current position from the converted buffer |
michael@0 | 75 | * and increments the current position |
michael@0 | 76 | * @param buf Pointer to UCHARBUF structure |
michael@0 | 77 | * @param err is a pointer to a valid <code>UErrorCode</code> value. If this value |
michael@0 | 78 | * indicates a failure on entry, the function will immediately return. |
michael@0 | 79 | * On exit the value will indicate the success of the operation. |
michael@0 | 80 | */ |
michael@0 | 81 | U_CAPI int32_t U_EXPORT2 |
michael@0 | 82 | ucbuf_getc32(UCHARBUF* buf,UErrorCode* err); |
michael@0 | 83 | |
michael@0 | 84 | /** |
michael@0 | 85 | * Gets a UTF-16 code unit at the current position from the converted buffer after |
michael@0 | 86 | * unescaping and increments the current position. If the escape sequence is for UTF-32 |
michael@0 | 87 | * code point (\\Uxxxxxxxx) then a UTF-32 codepoint is returned |
michael@0 | 88 | * @param buf Pointer to UCHARBUF structure |
michael@0 | 89 | * @param err is a pointer to a valid <code>UErrorCode</code> value. If this value |
michael@0 | 90 | * indicates a failure on entry, the function will immediately return. |
michael@0 | 91 | * On exit the value will indicate the success of the operation. |
michael@0 | 92 | */ |
michael@0 | 93 | U_CAPI int32_t U_EXPORT2 |
michael@0 | 94 | ucbuf_getcx32(UCHARBUF* buf,UErrorCode* err); |
michael@0 | 95 | |
michael@0 | 96 | /** |
michael@0 | 97 | * Gets a pointer to the current position in the internal buffer and length of the line. |
michael@0 | 98 | * It imperative to make a copy of the returned buffere before performing operations on it. |
michael@0 | 99 | * @param buf Pointer to UCHARBUF structure |
michael@0 | 100 | * @param len Output param to receive the len of the buffer returned till end of the line |
michael@0 | 101 | * @param err is a pointer to a valid <code>UErrorCode</code> value. If this value |
michael@0 | 102 | * indicates a failure on entry, the function will immediately return. |
michael@0 | 103 | * On exit the value will indicate the success of the operation. |
michael@0 | 104 | * Error: U_TRUNCATED_CHAR_FOUND |
michael@0 | 105 | * @return Pointer to the internal buffer, NULL if EOF |
michael@0 | 106 | */ |
michael@0 | 107 | U_CAPI const UChar* U_EXPORT2 |
michael@0 | 108 | ucbuf_readline(UCHARBUF* buf,int32_t* len, UErrorCode* err); |
michael@0 | 109 | |
michael@0 | 110 | |
michael@0 | 111 | /** |
michael@0 | 112 | * Resets the buffers and the underlying file stream. |
michael@0 | 113 | * @param buf Pointer to UCHARBUF structure |
michael@0 | 114 | * @param err is a pointer to a valid <code>UErrorCode</code> value. If this value |
michael@0 | 115 | * indicates a failure on entry, the function will immediately return. |
michael@0 | 116 | * On exit the value will indicate the success of the operation. |
michael@0 | 117 | */ |
michael@0 | 118 | U_CAPI void U_EXPORT2 |
michael@0 | 119 | ucbuf_rewind(UCHARBUF* buf,UErrorCode* err); |
michael@0 | 120 | |
michael@0 | 121 | /** |
michael@0 | 122 | * Returns a pointer to the internal converted buffer |
michael@0 | 123 | * @param buf Pointer to UCHARBUF structure |
michael@0 | 124 | * @param len Pointer to int32_t to receive the lenth of buffer |
michael@0 | 125 | * @param err is a pointer to a valid <code>UErrorCode</code> value. If this value |
michael@0 | 126 | * indicates a failure on entry, the function will immediately return. |
michael@0 | 127 | * On exit the value will indicate the success of the operation. |
michael@0 | 128 | * @return Pointer to internal UChar buffer |
michael@0 | 129 | */ |
michael@0 | 130 | U_CAPI const UChar* U_EXPORT2 |
michael@0 | 131 | ucbuf_getBuffer(UCHARBUF* buf,int32_t* len,UErrorCode* err); |
michael@0 | 132 | |
michael@0 | 133 | /** |
michael@0 | 134 | * Closes the UCHARBUF structure members and cleans up the malloc'ed memory |
michael@0 | 135 | * @param buf Pointer to UCHARBUF structure |
michael@0 | 136 | */ |
michael@0 | 137 | U_CAPI void U_EXPORT2 |
michael@0 | 138 | ucbuf_close(UCHARBUF* buf); |
michael@0 | 139 | |
michael@0 | 140 | /** |
michael@0 | 141 | * Rewinds the buffer by one codepoint. Does not rewind over escaped characters. |
michael@0 | 142 | */ |
michael@0 | 143 | U_CAPI void U_EXPORT2 |
michael@0 | 144 | ucbuf_ungetc(int32_t ungetChar,UCHARBUF* buf); |
michael@0 | 145 | |
michael@0 | 146 | |
michael@0 | 147 | /** |
michael@0 | 148 | * Autodetects the encoding of the file stream. Only Unicode charsets are autodectected. |
michael@0 | 149 | * Some Unicode charsets are stateful and need byte identifiers to be converted also to bring |
michael@0 | 150 | * the converter to correct state for converting the rest of the stream. So the UConverter parameter |
michael@0 | 151 | * is necessary. |
michael@0 | 152 | * If the charset was autodetected, the caller must close both the input FileStream |
michael@0 | 153 | * and the converter. |
michael@0 | 154 | * |
michael@0 | 155 | * @param fileName The file name to be opened and encoding autodected |
michael@0 | 156 | * @param conv Output param to receive the opened converter if autodetected; NULL otherwise. |
michael@0 | 157 | * @param cp Output param to receive the detected encoding |
michael@0 | 158 | * @param err is a pointer to a valid <code>UErrorCode</code> value. If this value |
michael@0 | 159 | * indicates a failure on entry, the function will immediately return. |
michael@0 | 160 | * On exit the value will indicate the success of the operation. |
michael@0 | 161 | * @return The input FileStream if its charset was autodetected; NULL otherwise. |
michael@0 | 162 | */ |
michael@0 | 163 | U_CAPI FileStream * U_EXPORT2 |
michael@0 | 164 | ucbuf_autodetect(const char* fileName, const char** cp,UConverter** conv, |
michael@0 | 165 | int32_t* signatureLength, UErrorCode* status); |
michael@0 | 166 | |
michael@0 | 167 | /** |
michael@0 | 168 | * Autodetects the encoding of the file stream. Only Unicode charsets are autodectected. |
michael@0 | 169 | * Some Unicode charsets are stateful and need byte identifiers to be converted also to bring |
michael@0 | 170 | * the converter to correct state for converting the rest of the stream. So the UConverter parameter |
michael@0 | 171 | * is necessary. |
michael@0 | 172 | * If the charset was autodetected, the caller must close the converter. |
michael@0 | 173 | * |
michael@0 | 174 | * @param fileStream The file stream whose encoding is to be detected |
michael@0 | 175 | * @param conv Output param to receive the opened converter if autodetected; NULL otherwise. |
michael@0 | 176 | * @param cp Output param to receive the detected encoding |
michael@0 | 177 | * @param err is a pointer to a valid <code>UErrorCode</code> value. If this value |
michael@0 | 178 | * indicates a failure on entry, the function will immediately return. |
michael@0 | 179 | * On exit the value will indicate the success of the operation. |
michael@0 | 180 | * @return Boolean whether the Unicode charset was autodetected. |
michael@0 | 181 | */ |
michael@0 | 182 | |
michael@0 | 183 | U_CAPI UBool U_EXPORT2 |
michael@0 | 184 | ucbuf_autodetect_fs(FileStream* in, const char** cp, UConverter** conv, int32_t* signatureLength, UErrorCode* status); |
michael@0 | 185 | |
michael@0 | 186 | /** |
michael@0 | 187 | * Returns the approximate size in UChars required for converting the file to UChars |
michael@0 | 188 | */ |
michael@0 | 189 | U_CAPI int32_t U_EXPORT2 |
michael@0 | 190 | ucbuf_size(UCHARBUF* buf); |
michael@0 | 191 | |
michael@0 | 192 | U_CAPI const char* U_EXPORT2 |
michael@0 | 193 | ucbuf_resolveFileName(const char* inputDir, const char* fileName, char* target, int32_t* len, UErrorCode* status); |
michael@0 | 194 | |
michael@0 | 195 | #endif |
michael@0 | 196 | #endif |
michael@0 | 197 |