intl/icu/source/tools/toolutil/uparse.h@6474c204b198 (annotated)
intl/icu/source/tools/toolutil/uparse.h
Wed, 31 Dec 2014 06:09:35 +0100
- author
- Michael Schloh von Bennewitz <michael@schloh.com>
- date
- Wed, 31 Dec 2014 06:09:35 +0100
- changeset 0
- 6474c204b198
- permissions
- -rw-r--r--
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) 2000-2010, International Business Machines |
| michael@0 | 5 | * Corporation and others. All Rights Reserved. |
| michael@0 | 6 | * |
| michael@0 | 7 | ******************************************************************************* |
| michael@0 | 8 | * file name: uparse.h |
| michael@0 | 9 | * encoding: US-ASCII |
| michael@0 | 10 | * tab size: 8 (not used) |
| michael@0 | 11 | * indentation:4 |
| michael@0 | 12 | * |
| michael@0 | 13 | * created on: 2000apr18 |
| michael@0 | 14 | * created by: Markus W. Scherer |
| michael@0 | 15 | * |
| michael@0 | 16 | * This file provides a parser for files that are delimited by one single |
| michael@0 | 17 | * character like ';' or TAB. Example: the Unicode Character Properties files |
| michael@0 | 18 | * like UnicodeData.txt are semicolon-delimited. |
| michael@0 | 19 | */ |
| michael@0 | 20 | |
| michael@0 | 21 | #ifndef __UPARSE_H__ |
| michael@0 | 22 | #define __UPARSE_H__ |
| michael@0 | 23 | |
| michael@0 | 24 | #include "unicode/utypes.h" |
| michael@0 | 25 | |
| michael@0 | 26 | /** |
| michael@0 | 27 | * Is c an invariant-character whitespace? |
| michael@0 | 28 | * @param c invariant character |
| michael@0 | 29 | */ |
| michael@0 | 30 | #define U_IS_INV_WHITESPACE(c) ((c)==' ' || (c)=='\t' || (c)=='\r' || (c)=='\n') |
| michael@0 | 31 | |
| michael@0 | 32 | U_CDECL_BEGIN |
| michael@0 | 33 | |
| michael@0 | 34 | /** |
| michael@0 | 35 | * Skip space ' ' and TAB '\t' characters. |
| michael@0 | 36 | * |
| michael@0 | 37 | * @param s Pointer to characters. |
| michael@0 | 38 | * @return Pointer to first character at or after s that is not a space or TAB. |
| michael@0 | 39 | */ |
| michael@0 | 40 | U_CAPI const char * U_EXPORT2 |
| michael@0 | 41 | u_skipWhitespace(const char *s); |
| michael@0 | 42 | |
| michael@0 | 43 | /** |
| michael@0 | 44 | * Trim whitespace (including line endings) from the end of the string. |
| michael@0 | 45 | * |
| michael@0 | 46 | * @param s Pointer to the string. |
| michael@0 | 47 | * @return Pointer to the new end of the string. |
| michael@0 | 48 | */ |
| michael@0 | 49 | U_CAPI char * U_EXPORT2 |
| michael@0 | 50 | u_rtrim(char *s); |
| michael@0 | 51 | |
| michael@0 | 52 | /** Function type for u_parseDelimitedFile(). */ |
| michael@0 | 53 | typedef void U_CALLCONV |
| michael@0 | 54 | UParseLineFn(void *context, |
| michael@0 | 55 | char *fields[][2], |
| michael@0 | 56 | int32_t fieldCount, |
| michael@0 | 57 | UErrorCode *pErrorCode); |
| michael@0 | 58 | |
| michael@0 | 59 | /** |
| michael@0 | 60 | * Parser for files that are similar to UnicodeData.txt: |
| michael@0 | 61 | * This function opens the file and reads it line by line. It skips empty lines |
| michael@0 | 62 | * and comment lines that start with a '#'. |
| michael@0 | 63 | * All other lines are separated into fields with one delimiter character |
| michael@0 | 64 | * (semicolon for Unicode Properties files) between two fields. The last field in |
| michael@0 | 65 | * a line does not need to be terminated with a delimiter. |
| michael@0 | 66 | * |
| michael@0 | 67 | * For each line, after segmenting it, a line function is called. |
| michael@0 | 68 | * It gets passed the array of field start and limit pointers that is |
| michael@0 | 69 | * passed into this parser and filled by it for each line. |
| michael@0 | 70 | * For each field i of the line, the start pointer in fields[i][0] |
| michael@0 | 71 | * points to the beginning of the field, while the limit pointer in fields[i][1] |
| michael@0 | 72 | * points behind the field, i.e., to the delimiter or the line end. |
| michael@0 | 73 | * |
| michael@0 | 74 | * The context parameter of the line function is |
| michael@0 | 75 | * the same as the one for the parse function. |
| michael@0 | 76 | * |
| michael@0 | 77 | * The line function may modify the contents of the fields including the |
| michael@0 | 78 | * limit characters. |
| michael@0 | 79 | * |
| michael@0 | 80 | * If the file cannot be opened, or there is a parsing error or a field function |
| michael@0 | 81 | * sets *pErrorCode, then the parser returns with *pErrorCode set to an error code. |
| michael@0 | 82 | */ |
| michael@0 | 83 | U_CAPI void U_EXPORT2 |
| michael@0 | 84 | u_parseDelimitedFile(const char *filename, char delimiter, |
| michael@0 | 85 | char *fields[][2], int32_t fieldCount, |
| michael@0 | 86 | UParseLineFn *lineFn, void *context, |
| michael@0 | 87 | UErrorCode *pErrorCode); |
| michael@0 | 88 | |
| michael@0 | 89 | /** |
| michael@0 | 90 | * Parse a string of code points like 0061 0308 0300. |
| michael@0 | 91 | * s must end with either ';' or NUL. |
| michael@0 | 92 | * |
| michael@0 | 93 | * @return Number of code points. |
| michael@0 | 94 | */ |
| michael@0 | 95 | U_CAPI int32_t U_EXPORT2 |
| michael@0 | 96 | u_parseCodePoints(const char *s, |
| michael@0 | 97 | uint32_t *dest, int32_t destCapacity, |
| michael@0 | 98 | UErrorCode *pErrorCode); |
| michael@0 | 99 | |
| michael@0 | 100 | /** |
| michael@0 | 101 | * Parse a list of code points like 0061 0308 0300 |
| michael@0 | 102 | * into a UChar * string. |
| michael@0 | 103 | * s must end with either ';' or NUL. |
| michael@0 | 104 | * |
| michael@0 | 105 | * Set the first code point in *pFirst. |
| michael@0 | 106 | * |
| michael@0 | 107 | * @param s Input char * string. |
| michael@0 | 108 | * @param dest Output string buffer. |
| michael@0 | 109 | * @param destCapacity Capacity of dest in numbers of UChars. |
| michael@0 | 110 | * @param pFirst If pFirst!=NULL the *pFirst will be set to the first |
| michael@0 | 111 | * code point in the string. |
| michael@0 | 112 | * @param pErrorCode ICU error code. |
| michael@0 | 113 | * @return The length of the string in numbers of UChars. |
| michael@0 | 114 | */ |
| michael@0 | 115 | U_CAPI int32_t U_EXPORT2 |
| michael@0 | 116 | u_parseString(const char *s, |
| michael@0 | 117 | UChar *dest, int32_t destCapacity, |
| michael@0 | 118 | uint32_t *pFirst, |
| michael@0 | 119 | UErrorCode *pErrorCode); |
| michael@0 | 120 | |
| michael@0 | 121 | /** |
| michael@0 | 122 | * Parse a code point range like |
| michael@0 | 123 | * 0085 or |
| michael@0 | 124 | * 4E00..9FA5. |
| michael@0 | 125 | * |
| michael@0 | 126 | * s must contain such a range and end with either ';' or NUL. |
| michael@0 | 127 | * |
| michael@0 | 128 | * @return Length of code point range, end-start+1 |
| michael@0 | 129 | */ |
| michael@0 | 130 | U_CAPI int32_t U_EXPORT2 |
| michael@0 | 131 | u_parseCodePointRange(const char *s, |
| michael@0 | 132 | uint32_t *pStart, uint32_t *pEnd, |
| michael@0 | 133 | UErrorCode *pErrorCode); |
| michael@0 | 134 | |
| michael@0 | 135 | /** |
| michael@0 | 136 | * Same as u_parseCodePointRange() but the range may be terminated by |
| michael@0 | 137 | * any character. The position of the terminating character is returned via |
| michael@0 | 138 | * the *terminator output parameter. |
| michael@0 | 139 | */ |
| michael@0 | 140 | U_CAPI int32_t U_EXPORT2 |
| michael@0 | 141 | u_parseCodePointRangeAnyTerminator(const char *s, |
| michael@0 | 142 | uint32_t *pStart, uint32_t *pEnd, |
| michael@0 | 143 | const char **terminator, |
| michael@0 | 144 | UErrorCode *pErrorCode); |
| michael@0 | 145 | |
| michael@0 | 146 | U_CAPI int32_t U_EXPORT2 |
| michael@0 | 147 | u_parseUTF8(const char *source, int32_t sLen, char *dest, int32_t destCapacity, UErrorCode *status); |
| michael@0 | 148 | |
| michael@0 | 149 | U_CDECL_END |
| michael@0 | 150 | |
| michael@0 | 151 | #endif |
