1.1 --- /dev/null Thu Jan 01 00:00:00 1970 +0000
1.2 +++ b/intl/icu/source/tools/toolutil/ucbuf.h Wed Dec 31 06:09:35 2014 +0100
1.3 @@ -0,0 +1,197 @@
1.4 +/*
1.5 +*******************************************************************************
1.6 +*
1.7 +* Copyright (C) 1998-2008, International Business Machines
1.8 +* Corporation and others. All Rights Reserved.
1.9 +*
1.10 +*******************************************************************************
1.11 +*
1.12 +* File ucbuf.c
1.13 +*
1.14 +* Modification History:
1.15 +*
1.16 +* Date Name Description
1.17 +* 05/10/01 Ram Creation.
1.18 +*
1.19 +* This API reads in files and returns UChars
1.20 +*******************************************************************************
1.21 +*/
1.22 +
1.23 +#include "unicode/ucnv.h"
1.24 +#include "filestrm.h"
1.25 +
1.26 +#if !UCONFIG_NO_CONVERSION
1.27 +
1.28 +#ifndef UCBUF_H
1.29 +#define UCBUF_H 1
1.30 +
1.31 +typedef struct UCHARBUF UCHARBUF;
1.32 +/**
1.33 + * End of file value
1.34 + */
1.35 +#define U_EOF 0xFFFFFFFF
1.36 +/**
1.37 + * Error value if a sequence cannot be unescaped
1.38 + */
1.39 +#define U_ERR 0xFFFFFFFE
1.40 +
1.41 +typedef struct ULine ULine;
1.42 +
1.43 +struct ULine {
1.44 + UChar *name;
1.45 + int32_t len;
1.46 +};
1.47 +
1.48 +/**
1.49 + * Opens the UCHARBUF with the given file stream and code page for conversion
1.50 + * @param fileName Name of the file to open.
1.51 + * @param codepage The encoding of the file stream to convert to Unicode.
1.52 + * If *codepoge is NULL on input the API will try to autodetect
1.53 + * popular Unicode encodings
1.54 + * @param showWarning Flag to print out warnings to STDOUT
1.55 + * @param buffered If TRUE performs a buffered read of the input file. If FALSE reads
1.56 + * the whole file into memory and converts it.
1.57 + * @param err is a pointer to a valid <code>UErrorCode</code> value. If this value
1.58 + * indicates a failure on entry, the function will immediately return.
1.59 + * On exit the value will indicate the success of the operation.
1.60 + * @return pointer to the newly opened UCHARBUF
1.61 + */
1.62 +U_CAPI UCHARBUF* U_EXPORT2
1.63 +ucbuf_open(const char* fileName,const char** codepage,UBool showWarning, UBool buffered, UErrorCode* err);
1.64 +
1.65 +/**
1.66 + * Gets a UTF-16 code unit at the current position from the converted buffer
1.67 + * and increments the current position
1.68 + * @param buf Pointer to UCHARBUF structure
1.69 + * @param err is a pointer to a valid <code>UErrorCode</code> value. If this value
1.70 + * indicates a failure on entry, the function will immediately return.
1.71 + * On exit the value will indicate the success of the operation.
1.72 + */
1.73 +U_CAPI int32_t U_EXPORT2
1.74 +ucbuf_getc(UCHARBUF* buf,UErrorCode* err);
1.75 +
1.76 +/**
1.77 + * Gets a UTF-32 code point at the current position from the converted buffer
1.78 + * and increments the current position
1.79 + * @param buf Pointer to UCHARBUF structure
1.80 + * @param err is a pointer to a valid <code>UErrorCode</code> value. If this value
1.81 + * indicates a failure on entry, the function will immediately return.
1.82 + * On exit the value will indicate the success of the operation.
1.83 + */
1.84 +U_CAPI int32_t U_EXPORT2
1.85 +ucbuf_getc32(UCHARBUF* buf,UErrorCode* err);
1.86 +
1.87 +/**
1.88 + * Gets a UTF-16 code unit at the current position from the converted buffer after
1.89 + * unescaping and increments the current position. If the escape sequence is for UTF-32
1.90 + * code point (\\Uxxxxxxxx) then a UTF-32 codepoint is returned
1.91 + * @param buf Pointer to UCHARBUF structure
1.92 + * @param err is a pointer to a valid <code>UErrorCode</code> value. If this value
1.93 + * indicates a failure on entry, the function will immediately return.
1.94 + * On exit the value will indicate the success of the operation.
1.95 + */
1.96 +U_CAPI int32_t U_EXPORT2
1.97 +ucbuf_getcx32(UCHARBUF* buf,UErrorCode* err);
1.98 +
1.99 +/**
1.100 + * Gets a pointer to the current position in the internal buffer and length of the line.
1.101 + * It imperative to make a copy of the returned buffere before performing operations on it.
1.102 + * @param buf Pointer to UCHARBUF structure
1.103 + * @param len Output param to receive the len of the buffer returned till end of the line
1.104 + * @param err is a pointer to a valid <code>UErrorCode</code> value. If this value
1.105 + * indicates a failure on entry, the function will immediately return.
1.106 + * On exit the value will indicate the success of the operation.
1.107 + * Error: U_TRUNCATED_CHAR_FOUND
1.108 + * @return Pointer to the internal buffer, NULL if EOF
1.109 + */
1.110 +U_CAPI const UChar* U_EXPORT2
1.111 +ucbuf_readline(UCHARBUF* buf,int32_t* len, UErrorCode* err);
1.112 +
1.113 +
1.114 +/**
1.115 + * Resets the buffers and the underlying file stream.
1.116 + * @param buf Pointer to UCHARBUF structure
1.117 + * @param err is a pointer to a valid <code>UErrorCode</code> value. If this value
1.118 + * indicates a failure on entry, the function will immediately return.
1.119 + * On exit the value will indicate the success of the operation.
1.120 + */
1.121 +U_CAPI void U_EXPORT2
1.122 +ucbuf_rewind(UCHARBUF* buf,UErrorCode* err);
1.123 +
1.124 +/**
1.125 + * Returns a pointer to the internal converted buffer
1.126 + * @param buf Pointer to UCHARBUF structure
1.127 + * @param len Pointer to int32_t to receive the lenth of buffer
1.128 + * @param err is a pointer to a valid <code>UErrorCode</code> value. If this value
1.129 + * indicates a failure on entry, the function will immediately return.
1.130 + * On exit the value will indicate the success of the operation.
1.131 + * @return Pointer to internal UChar buffer
1.132 + */
1.133 +U_CAPI const UChar* U_EXPORT2
1.134 +ucbuf_getBuffer(UCHARBUF* buf,int32_t* len,UErrorCode* err);
1.135 +
1.136 +/**
1.137 + * Closes the UCHARBUF structure members and cleans up the malloc'ed memory
1.138 + * @param buf Pointer to UCHARBUF structure
1.139 + */
1.140 +U_CAPI void U_EXPORT2
1.141 +ucbuf_close(UCHARBUF* buf);
1.142 +
1.143 +/**
1.144 + * Rewinds the buffer by one codepoint. Does not rewind over escaped characters.
1.145 + */
1.146 +U_CAPI void U_EXPORT2
1.147 +ucbuf_ungetc(int32_t ungetChar,UCHARBUF* buf);
1.148 +
1.149 +
1.150 +/**
1.151 + * Autodetects the encoding of the file stream. Only Unicode charsets are autodectected.
1.152 + * Some Unicode charsets are stateful and need byte identifiers to be converted also to bring
1.153 + * the converter to correct state for converting the rest of the stream. So the UConverter parameter
1.154 + * is necessary.
1.155 + * If the charset was autodetected, the caller must close both the input FileStream
1.156 + * and the converter.
1.157 + *
1.158 + * @param fileName The file name to be opened and encoding autodected
1.159 + * @param conv Output param to receive the opened converter if autodetected; NULL otherwise.
1.160 + * @param cp Output param to receive the detected encoding
1.161 + * @param err is a pointer to a valid <code>UErrorCode</code> value. If this value
1.162 + * indicates a failure on entry, the function will immediately return.
1.163 + * On exit the value will indicate the success of the operation.
1.164 + * @return The input FileStream if its charset was autodetected; NULL otherwise.
1.165 + */
1.166 +U_CAPI FileStream * U_EXPORT2
1.167 +ucbuf_autodetect(const char* fileName, const char** cp,UConverter** conv,
1.168 +int32_t* signatureLength, UErrorCode* status);
1.169 +
1.170 +/**
1.171 + * Autodetects the encoding of the file stream. Only Unicode charsets are autodectected.
1.172 + * Some Unicode charsets are stateful and need byte identifiers to be converted also to bring
1.173 + * the converter to correct state for converting the rest of the stream. So the UConverter parameter
1.174 + * is necessary.
1.175 + * If the charset was autodetected, the caller must close the converter.
1.176 + *
1.177 + * @param fileStream The file stream whose encoding is to be detected
1.178 + * @param conv Output param to receive the opened converter if autodetected; NULL otherwise.
1.179 + * @param cp Output param to receive the detected encoding
1.180 + * @param err is a pointer to a valid <code>UErrorCode</code> value. If this value
1.181 + * indicates a failure on entry, the function will immediately return.
1.182 + * On exit the value will indicate the success of the operation.
1.183 + * @return Boolean whether the Unicode charset was autodetected.
1.184 + */
1.185 +
1.186 +U_CAPI UBool U_EXPORT2
1.187 +ucbuf_autodetect_fs(FileStream* in, const char** cp, UConverter** conv, int32_t* signatureLength, UErrorCode* status);
1.188 +
1.189 +/**
1.190 + * Returns the approximate size in UChars required for converting the file to UChars
1.191 + */
1.192 +U_CAPI int32_t U_EXPORT2
1.193 +ucbuf_size(UCHARBUF* buf);
1.194 +
1.195 +U_CAPI const char* U_EXPORT2
1.196 +ucbuf_resolveFileName(const char* inputDir, const char* fileName, char* target, int32_t* len, UErrorCode* status);
1.197 +
1.198 +#endif
1.199 +#endif
1.200 +
