|
ICU 76.1 76.1
|
C API: Regular Expressions. More...
#include "unicode/utext.h"#include "unicode/utypes.h"#include "unicode/parseerr.h"#include "unicode/localpointer.h"Go to the source code of this file.
Namespaces | |
| namespace | icu |
| File coll.h. | |
Typedefs | |
| typedef struct URegularExpression | URegularExpression |
| Structure representing a compiled regular expression, plus the results of a match operation. | |
| typedef enum URegexpFlag | URegexpFlag |
| Constants for Regular Expression Match Modes. | |
| typedef UBool | URegexMatchCallback(const void *context, int32_t steps) |
| Function pointer for a regular expression matching callback function. | |
| typedef UBool | URegexFindProgressCallback(const void *context, int64_t matchIndex) |
| Function pointer for a regular expression find callback function. | |
Enumerations | |
| enum | URegexpFlag { UREGEX_CANON_EQ = 128 , UREGEX_CASE_INSENSITIVE = 2 , UREGEX_COMMENTS = 4 , UREGEX_DOTALL = 32 , UREGEX_LITERAL = 16 , UREGEX_MULTILINE = 8 , UREGEX_UNIX_LINES = 1 , UREGEX_UWORD = 256 , UREGEX_ERROR_ON_UNKNOWN_ESCAPES = 512 } |
| Constants for Regular Expression Match Modes. More... | |
Functions | |
| U_CAPI URegularExpression * | uregex_open (const UChar *pattern, int32_t patternLength, uint32_t flags, UParseError *pe, UErrorCode *status) |
| Open (compile) an ICU regular expression. | |
| U_CAPI URegularExpression * | uregex_openUText (UText *pattern, uint32_t flags, UParseError *pe, UErrorCode *status) |
| Open (compile) an ICU regular expression. | |
| U_CAPI URegularExpression * | uregex_openC (const char *pattern, uint32_t flags, UParseError *pe, UErrorCode *status) |
| Open (compile) an ICU regular expression. | |
| U_CAPI void | uregex_close (URegularExpression *regexp) |
| Close the regular expression, recovering all resources (memory) it was holding. | |
| U_CAPI URegularExpression * | uregex_clone (const URegularExpression *regexp, UErrorCode *status) |
| Make a copy of a compiled regular expression. | |
| U_CAPI const UChar * | uregex_pattern (const URegularExpression *regexp, int32_t *patLength, UErrorCode *status) |
| Returns a pointer to the source form of the pattern for this regular expression. | |
| U_CAPI UText * | uregex_patternUText (const URegularExpression *regexp, UErrorCode *status) |
| Returns the source text of the pattern for this regular expression. | |
| U_CAPI int32_t | uregex_flags (const URegularExpression *regexp, UErrorCode *status) |
| Get the match mode flags that were specified when compiling this regular expression. | |
| U_CAPI void | uregex_setText (URegularExpression *regexp, const UChar *text, int32_t textLength, UErrorCode *status) |
| Set the subject text string upon which the regular expression will look for matches. | |
| U_CAPI void | uregex_setUText (URegularExpression *regexp, UText *text, UErrorCode *status) |
| Set the subject text string upon which the regular expression will look for matches. | |
| U_CAPI const UChar * | uregex_getText (URegularExpression *regexp, int32_t *textLength, UErrorCode *status) |
| Get the subject text that is currently associated with this regular expression object. | |
| U_CAPI UText * | uregex_getUText (URegularExpression *regexp, UText *dest, UErrorCode *status) |
| Get the subject text that is currently associated with this regular expression object. | |
| U_CAPI void | uregex_refreshUText (URegularExpression *regexp, UText *text, UErrorCode *status) |
| Set the subject text string upon which the regular expression is looking for matches without changing any other aspect of the matching state. | |
| U_CAPI UBool | uregex_matches (URegularExpression *regexp, int32_t startIndex, UErrorCode *status) |
| Attempts to match the input string against the pattern. | |
| U_CAPI UBool | uregex_matches64 (URegularExpression *regexp, int64_t startIndex, UErrorCode *status) |
| 64bit version of uregex_matches. | |
| U_CAPI UBool | uregex_lookingAt (URegularExpression *regexp, int32_t startIndex, UErrorCode *status) |
| Attempts to match the input string, starting from the specified index, against the pattern. | |
| U_CAPI UBool | uregex_lookingAt64 (URegularExpression *regexp, int64_t startIndex, UErrorCode *status) |
| 64bit version of uregex_lookingAt. | |
| U_CAPI UBool | uregex_find (URegularExpression *regexp, int32_t startIndex, UErrorCode *status) |
| Find the first matching substring of the input string that matches the pattern. | |
| U_CAPI UBool | uregex_find64 (URegularExpression *regexp, int64_t startIndex, UErrorCode *status) |
| 64bit version of uregex_find. | |
| U_CAPI UBool | uregex_findNext (URegularExpression *regexp, UErrorCode *status) |
| Find the next pattern match in the input string. | |
| U_CAPI int32_t | uregex_groupCount (URegularExpression *regexp, UErrorCode *status) |
| Get the number of capturing groups in this regular expression's pattern. | |
| U_CAPI int32_t | uregex_groupNumberFromName (URegularExpression *regexp, const UChar *groupName, int32_t nameLength, UErrorCode *status) |
| Get the group number corresponding to a named capture group. | |
| U_CAPI int32_t | uregex_groupNumberFromCName (URegularExpression *regexp, const char *groupName, int32_t nameLength, UErrorCode *status) |
| Get the group number corresponding to a named capture group. | |
| U_CAPI int32_t | uregex_group (URegularExpression *regexp, int32_t groupNum, UChar *dest, int32_t destCapacity, UErrorCode *status) |
| Extract the string for the specified matching expression or subexpression. | |
| U_CAPI UText * | uregex_groupUText (URegularExpression *regexp, int32_t groupNum, UText *dest, int64_t *groupLength, UErrorCode *status) |
| Returns a shallow immutable clone of the entire input string with the current index set to the beginning of the requested capture group. | |
| U_CAPI int32_t | uregex_start (URegularExpression *regexp, int32_t groupNum, UErrorCode *status) |
| Returns the index in the input string of the start of the text matched by the specified capture group during the previous match operation. | |
| U_CAPI int64_t | uregex_start64 (URegularExpression *regexp, int32_t groupNum, UErrorCode *status) |
| 64bit version of uregex_start. | |
| U_CAPI int32_t | uregex_end (URegularExpression *regexp, int32_t groupNum, UErrorCode *status) |
| Returns the index in the input string of the position following the end of the text matched by the specified capture group. | |
| U_CAPI int64_t | uregex_end64 (URegularExpression *regexp, int32_t groupNum, UErrorCode *status) |
| 64bit version of uregex_end. | |
| U_CAPI void | uregex_reset (URegularExpression *regexp, int32_t index, UErrorCode *status) |
| Reset any saved state from the previous match. | |
| U_CAPI void | uregex_reset64 (URegularExpression *regexp, int64_t index, UErrorCode *status) |
| 64bit version of uregex_reset. | |
| U_CAPI void | uregex_setRegion (URegularExpression *regexp, int32_t regionStart, int32_t regionLimit, UErrorCode *status) |
| Sets the limits of the matching region for this URegularExpression. | |
| U_CAPI void | uregex_setRegion64 (URegularExpression *regexp, int64_t regionStart, int64_t regionLimit, UErrorCode *status) |
| 64bit version of uregex_setRegion. | |
| U_CAPI void | uregex_setRegionAndStart (URegularExpression *regexp, int64_t regionStart, int64_t regionLimit, int64_t startIndex, UErrorCode *status) |
| Set the matching region and the starting index for subsequent matches in a single operation. | |
| U_CAPI int32_t | uregex_regionStart (const URegularExpression *regexp, UErrorCode *status) |
| Reports the start index of the matching region. | |
| U_CAPI int64_t | uregex_regionStart64 (const URegularExpression *regexp, UErrorCode *status) |
| 64bit version of uregex_regionStart. | |
| U_CAPI int32_t | uregex_regionEnd (const URegularExpression *regexp, UErrorCode *status) |
| Reports the end index (exclusive) of the matching region for this URegularExpression. | |
| U_CAPI int64_t | uregex_regionEnd64 (const URegularExpression *regexp, UErrorCode *status) |
| 64bit version of uregex_regionEnd. | |
| U_CAPI UBool | uregex_hasTransparentBounds (const URegularExpression *regexp, UErrorCode *status) |
| Queries the transparency of region bounds for this URegularExpression. | |
| U_CAPI void | uregex_useTransparentBounds (URegularExpression *regexp, UBool b, UErrorCode *status) |
| Sets the transparency of region bounds for this URegularExpression. | |
| U_CAPI UBool | uregex_hasAnchoringBounds (const URegularExpression *regexp, UErrorCode *status) |
| Return true if this URegularExpression is using anchoring bounds. | |
| U_CAPI void | uregex_useAnchoringBounds (URegularExpression *regexp, UBool b, UErrorCode *status) |
| Set whether this URegularExpression is using Anchoring Bounds for its region. | |
| U_CAPI UBool | uregex_hitEnd (const URegularExpression *regexp, UErrorCode *status) |
| Return true if the most recent matching operation touched the end of the text being processed. | |
| U_CAPI UBool | uregex_requireEnd (const URegularExpression *regexp, UErrorCode *status) |
| Return true the most recent match succeeded and additional input could cause it to fail. | |
| U_CAPI int32_t | uregex_replaceAll (URegularExpression *regexp, const UChar *replacementText, int32_t replacementLength, UChar *destBuf, int32_t destCapacity, UErrorCode *status) |
| Replaces every substring of the input that matches the pattern with the given replacement string. | |
| U_CAPI UText * | uregex_replaceAllUText (URegularExpression *regexp, UText *replacement, UText *dest, UErrorCode *status) |
| Replaces every substring of the input that matches the pattern with the given replacement string. | |
| U_CAPI int32_t | uregex_replaceFirst (URegularExpression *regexp, const UChar *replacementText, int32_t replacementLength, UChar *destBuf, int32_t destCapacity, UErrorCode *status) |
| Replaces the first substring of the input that matches the pattern with the given replacement string. | |
| U_CAPI UText * | uregex_replaceFirstUText (URegularExpression *regexp, UText *replacement, UText *dest, UErrorCode *status) |
| Replaces the first substring of the input that matches the pattern with the given replacement string. | |
| U_CAPI int32_t | uregex_appendReplacement (URegularExpression *regexp, const UChar *replacementText, int32_t replacementLength, UChar **destBuf, int32_t *destCapacity, UErrorCode *status) |
| Implements a replace operation intended to be used as part of an incremental find-and-replace. | |
| U_CAPI void | uregex_appendReplacementUText (URegularExpression *regexp, UText *replacementText, UText *dest, UErrorCode *status) |
| Implements a replace operation intended to be used as part of an incremental find-and-replace. | |
| U_CAPI int32_t | uregex_appendTail (URegularExpression *regexp, UChar **destBuf, int32_t *destCapacity, UErrorCode *status) |
| As the final step in a find-and-replace operation, append the remainder of the input string, starting at the position following the last match, to the destination string. | |
| U_CAPI UText * | uregex_appendTailUText (URegularExpression *regexp, UText *dest, UErrorCode *status) |
| As the final step in a find-and-replace operation, append the remainder of the input string, starting at the position following the last match, to the destination string. | |
| U_CAPI int32_t | uregex_split (URegularExpression *regexp, UChar *destBuf, int32_t destCapacity, int32_t *requiredCapacity, UChar *destFields[], int32_t destFieldsCapacity, UErrorCode *status) |
| Split a string into fields. | |
| U_CAPI int32_t | uregex_splitUText (URegularExpression *regexp, UText *destFields[], int32_t destFieldsCapacity, UErrorCode *status) |
| Split a string into fields. | |
| U_CAPI void | uregex_setTimeLimit (URegularExpression *regexp, int32_t limit, UErrorCode *status) |
| Set a processing time limit for match operations with this URegularExpression. | |
| U_CAPI int32_t | uregex_getTimeLimit (const URegularExpression *regexp, UErrorCode *status) |
| Get the time limit for for matches with this URegularExpression. | |
| U_CAPI void | uregex_setStackLimit (URegularExpression *regexp, int32_t limit, UErrorCode *status) |
| Set the amount of heap storage available for use by the match backtracking stack. | |
| U_CAPI int32_t | uregex_getStackLimit (const URegularExpression *regexp, UErrorCode *status) |
| Get the size of the heap storage available for use by the back tracking stack. | |
| U_CAPI void | uregex_setMatchCallback (URegularExpression *regexp, URegexMatchCallback *callback, const void *context, UErrorCode *status) |
| Set a callback function for this URegularExpression. | |
| U_CAPI void | uregex_getMatchCallback (const URegularExpression *regexp, URegexMatchCallback **callback, const void **context, UErrorCode *status) |
| Get the callback function for this URegularExpression. | |
| U_CAPI void | uregex_setFindProgressCallback (URegularExpression *regexp, URegexFindProgressCallback *callback, const void *context, UErrorCode *status) |
| Set the find progress callback function for this URegularExpression. | |
| U_CAPI void | uregex_getFindProgressCallback (const URegularExpression *regexp, URegexFindProgressCallback **callback, const void **context, UErrorCode *status) |
| Get the find progress callback function for this URegularExpression. | |
C API: Regular Expressions.
This is a C wrapper around the C++ RegexPattern and RegexMatcher classes.
Definition in file uregex.h.
| typedef UBool URegexFindProgressCallback(const void *context, int64_t matchIndex) |
Function pointer for a regular expression find callback function.
When set, a callback function will be called during a find operation and for operations that depend on find, such as findNext, split and some replace operations like replaceFirst. The callback will usually be called after each attempt at a match, but this is not a guarantee that the callback will be invoked at each character. For finds where the match engine is invoked at each character, this may be close to true, but less likely for more optimized loops where the pattern is known to only start, and the match engine invoked, at certain characters. When invoked, this callback will specify the index at which a match operation is about to be attempted, giving the application the opportunity to terminate a long-running find operation.
If the call back function returns false, the find operation will be terminated early.
Note: the callback function must not call other functions on this URegularExpression
| context | context pointer. The callback function will be invoked with the context specified at the time that uregex_setFindProgressCallback() is called. |
| matchIndex | the next index at which a match attempt will be attempted for this find operation. If this callback interrupts the search, this is the index at which a find/findNext operation may be re-initiated. |
| typedef UBool URegexMatchCallback(const void *context, int32_t steps) |
Function pointer for a regular expression matching callback function.
When set, a callback function will be called periodically during matching operations. If the call back function returns false, the matching operation will be terminated early.
Note: the callback function must not call other functions on this URegularExpression.
| context | context pointer. The callback function will be invoked with the context specified at the time that uregex_setMatchCallback() is called. |
| steps | the accumulated processing time, in match steps, for this matching operation. |
| typedef enum URegexpFlag URegexpFlag |
Constants for Regular Expression Match Modes.
| typedef struct URegularExpression URegularExpression |
| enum URegexpFlag |
Constants for Regular Expression Match Modes.
| Enumerator | |
|---|---|
| UREGEX_CANON_EQ | Forces normalization of pattern and strings. Not implemented yet, just a placeholder, hence draft.
|
| UREGEX_CASE_INSENSITIVE | Enable case insensitive matching.
|
| UREGEX_COMMENTS | Allow white space and comments within patterns.
|
| UREGEX_DOTALL | If set, '. ' matches line terminators, otherwise '.' matching stops at line end.
|
| UREGEX_LITERAL | If set, treat the entire pattern as a literal string.
The flag UREGEX_CASE_INSENSITIVE retains its impact on matching when used in conjunction with this flag. The other flags become superfluous.
|
| UREGEX_MULTILINE | Control behavior of "$" and "^" If set, recognize line terminators within string, otherwise, match only at start and end of input string.
|
| UREGEX_UNIX_LINES | Unix-only line endings. When this mode is enabled, only \u000a is recognized as a line ending in the behavior of ., ^, and $.
|
| UREGEX_UWORD | Unicode word boundaries. If set, uses the Unicode TR 29 definition of word boundaries. Warning: Unicode word boundaries are quite different from traditional regular expression word boundaries. See http://unicode.org/reports/tr29/#Word_Boundaries
|
| UREGEX_ERROR_ON_UNKNOWN_ESCAPES | Error on Unrecognized backslash escapes. If set, fail with an error on patterns that contain backslash-escaped ASCII letters without a known special meaning. If this flag is not set, these escaped letters represent themselves.
|
| U_CAPI int32_t uregex_appendReplacement | ( | URegularExpression * | regexp, |
| const UChar * | replacementText, | ||
| int32_t | replacementLength, | ||
| UChar ** | destBuf, | ||
| int32_t * | destCapacity, | ||
| UErrorCode * | status | ||
| ) |
Implements a replace operation intended to be used as part of an incremental find-and-replace.
The input string, starting from the end of the previous match and ending at the start of the current match, is appended to the destination string. Then the replacement string is appended to the output string, including handling any substitutions of captured text.
A note on preflight computation of buffersize and error handling: Calls to uregex_appendReplacement() and uregex_appendTail() are designed to be chained, one after another, with the destination buffer pointer and buffer capacity updated after each in preparation to for the next. If the destination buffer is exhausted partway through such a sequence, a U_BUFFER_OVERFLOW_ERROR status will be returned. Normal ICU conventions are for a function to perform no action if it is called with an error status, but for this one case, uregex_appendRepacement() will operate normally so that buffer size computations will complete correctly.
For simple, prepackaged, non-incremental find-and-replace operations, see replaceFirst() or replaceAll().
| regexp | The regular expression object. |
| replacementText | The string that will replace the matched portion of the input string as it is copied to the destination buffer. The replacement text may contain references ($1, for example) to capture groups from the match. |
| replacementLength | The length of the replacement text string, or -1 if the string is NUL terminated. |
| destBuf | The buffer into which the results of the find-and-replace are placed. On return, this pointer will be updated to refer to the beginning of the unused portion of buffer, leaving it in position for a subsequent call to this function. |
| destCapacity | The size of the output buffer, On return, this parameter will be updated to reflect the space remaining unused in the output buffer. |
| status | A reference to a UErrorCode to receive any errors. |
| U_CAPI void uregex_appendReplacementUText | ( | URegularExpression * | regexp, |
| UText * | replacementText, | ||
| UText * | dest, | ||
| UErrorCode * | status | ||
| ) |
Implements a replace operation intended to be used as part of an incremental find-and-replace.
The input string, starting from the end of the previous match and ending at the start of the current match, is appended to the destination string. Then the replacement string is appended to the output string, including handling any substitutions of captured text.
For simple, prepackaged, non-incremental find-and-replace operations, see replaceFirst() or replaceAll().
| regexp | The regular expression object. |
| replacementText | The string that will replace the matched portion of the input string as it is copied to the destination buffer. The replacement text may contain references ($1, for example) to capture groups from the match. |
| dest | A mutable UText that will receive the result. Must not be NULL. |
| status | A reference to a UErrorCode to receive any errors. |
| U_CAPI int32_t uregex_appendTail | ( | URegularExpression * | regexp, |
| UChar ** | destBuf, | ||
| int32_t * | destCapacity, | ||
| UErrorCode * | status | ||
| ) |
As the final step in a find-and-replace operation, append the remainder of the input string, starting at the position following the last match, to the destination string.
uregex_appendTail() is intended to be invoked after one or more invocations of the uregex_appendReplacement() function.
| regexp | The regular expression object. This is needed to obtain the input string and with the position of the last match within it. |
| destBuf | The buffer in which the results of the find-and-replace are placed. On return, the pointer will be updated to refer to the beginning of the unused portion of buffer. |
| destCapacity | The size of the output buffer, On return, this value will be updated to reflect the space remaining unused in the output buffer. |
| status | A reference to a UErrorCode to receive any errors. |
| U_CAPI UText * uregex_appendTailUText | ( | URegularExpression * | regexp, |
| UText * | dest, | ||
| UErrorCode * | status | ||
| ) |
As the final step in a find-and-replace operation, append the remainder of the input string, starting at the position following the last match, to the destination string.
uregex_appendTailUText() is intended to be invoked after one or more invocations of the uregex_appendReplacementUText() function.
| regexp | The regular expression object. This is needed to obtain the input string and with the position of the last match within it. |
| dest | A mutable UText that will receive the result. Must not be NULL. |
| status | Error code |
| U_CAPI URegularExpression * uregex_clone | ( | const URegularExpression * | regexp, |
| UErrorCode * | status | ||
| ) |
Make a copy of a compiled regular expression.
Cloning a regular expression is faster than opening a second instance from the source form of the expression, and requires less memory.
Note that the current input string and the position of any matched text within it are not cloned; only the pattern itself and the match mode flags are copied.
Cloning can be particularly useful to threaded applications that perform multiple match operations in parallel. Each concurrent RE operation requires its own instance of a URegularExpression.
| regexp | The compiled regular expression to be cloned. |
| status | Receives indication of any errors encountered |
| U_CAPI void uregex_close | ( | URegularExpression * | regexp | ) |
Close the regular expression, recovering all resources (memory) it was holding.
| regexp | The regular expression to be closed. |
| U_CAPI int32_t uregex_end | ( | URegularExpression * | regexp, |
| int32_t | groupNum, | ||
| UErrorCode * | status | ||
| ) |
Returns the index in the input string of the position following the end of the text matched by the specified capture group.
Return -1 if the capture group was not part of the last match. Group #0 refers to the complete range of matched text. Group #1 refers to the text matched by the first set of capturing parentheses.
| regexp | The compiled regular expression. |
| groupNum | The capture group number |
| status | A reference to a UErrorCode to receive any errors. |
| U_CAPI int64_t uregex_end64 | ( | URegularExpression * | regexp, |
| int32_t | groupNum, | ||
| UErrorCode * | status | ||
| ) |
64bit version of uregex_end.
Returns the index in the input string of the position following the end of the text matched by the specified capture group. Return -1 if the capture group was not part of the last match. Group #0 refers to the complete range of matched text. Group #1 refers to the text matched by the first set of capturing parentheses.
| regexp | The compiled regular expression. |
| groupNum | The capture group number |
| status | A reference to a UErrorCode to receive any errors. |
| U_CAPI UBool uregex_find | ( | URegularExpression * | regexp, |
| int32_t | startIndex, | ||
| UErrorCode * | status | ||
| ) |
Find the first matching substring of the input string that matches the pattern.
If startIndex is >= zero the search for a match begins at the specified index, and any match region is reset. This corresponds directly with Matcher.find(startIndex) in Java.
If startIndex == -1 the search begins at the start of the input region, or at the start of the full string if no region has been specified.
If a match is found, uregex_start(), uregex_end(), and uregex_group() will provide more information regarding the match.
| regexp | The compiled regular expression. |
| startIndex | The position (native) in the input string to begin the search, or -1 to search within the Input Region. |
| status | A reference to a UErrorCode to receive any errors. |
| U_CAPI UBool uregex_find64 | ( | URegularExpression * | regexp, |
| int64_t | startIndex, | ||
| UErrorCode * | status | ||
| ) |
64bit version of uregex_find.
Find the first matching substring of the input string that matches the pattern. If startIndex is >= zero the search for a match begins at the specified index, and any match region is reset. This corresponds directly with Matcher.find(startIndex) in Java.
If startIndex == -1 the search begins at the start of the input region, or at the start of the full string if no region has been specified.
If a match is found, uregex_start(), uregex_end(), and uregex_group() will provide more information regarding the match.
| regexp | The compiled regular expression. |
| startIndex | The position (native) in the input string to begin the search, or -1 to search within the Input Region. |
| status | A reference to a UErrorCode to receive any errors. |
| U_CAPI UBool uregex_findNext | ( | URegularExpression * | regexp, |
| UErrorCode * | status | ||
| ) |
Find the next pattern match in the input string.
Begin searching the input at the location following the end of he previous match, or at the start of the string (or region) if there is no previous match. If a match is found, uregex_start(), uregex_end(), and uregex_group() will provide more information regarding the match.
| regexp | The compiled regular expression. |
| status | A reference to a UErrorCode to receive any errors. |
| U_CAPI int32_t uregex_flags | ( | const URegularExpression * | regexp, |
| UErrorCode * | status | ||
| ) |
Get the match mode flags that were specified when compiling this regular expression.
| status | Receives errors detected by this function. |
| regexp | The compiled regular expression. |
| U_CAPI void uregex_getFindProgressCallback | ( | const URegularExpression * | regexp, |
| URegexFindProgressCallback ** | callback, | ||
| const void ** | context, | ||
| UErrorCode * | status | ||
| ) |
Get the find progress callback function for this URegularExpression.
| regexp | The compiled regular expression. |
| callback | Out parameter, receives a pointer to the user-supplied callback function. |
| context | Out parameter, receives the user context pointer that was set when uregex_setFindProgressCallback() was called. |
| status | A reference to a UErrorCode to receive any errors. |
| U_CAPI void uregex_getMatchCallback | ( | const URegularExpression * | regexp, |
| URegexMatchCallback ** | callback, | ||
| const void ** | context, | ||
| UErrorCode * | status | ||
| ) |
Get the callback function for this URegularExpression.
| regexp | The compiled regular expression. |
| callback | Out parameter, receives a pointer to the user-supplied callback function. |
| context | Out parameter, receives the user context pointer that was set when uregex_setMatchCallback() was called. |
| status | A reference to a UErrorCode to receive any errors. |
| U_CAPI int32_t uregex_getStackLimit | ( | const URegularExpression * | regexp, |
| UErrorCode * | status | ||
| ) |
Get the size of the heap storage available for use by the back tracking stack.
| U_CAPI const UChar * uregex_getText | ( | URegularExpression * | regexp, |
| int32_t * | textLength, | ||
| UErrorCode * | status | ||
| ) |
Get the subject text that is currently associated with this regular expression object.
If the input was supplied using uregex_setText(), that pointer will be returned. Otherwise, the characters in the input will be extracted to a buffer and returned. In either case, ownership remains with the regular expression object.
This function will work even if the input was originally specified as a UText.
| regexp | The compiled regular expression. |
| textLength | The length of the string is returned in this output parameter. A NULL pointer may be used here if the text length is not needed, as would be the case if the text is known in advance to be a NUL terminated string. |
| status | Receives errors detected by this function. |
| U_CAPI int32_t uregex_getTimeLimit | ( | const URegularExpression * | regexp, |
| UErrorCode * | status | ||
| ) |
Get the time limit for for matches with this URegularExpression.
A return value of zero indicates that there is no limit.
| regexp | The compiled regular expression. |
| status | A reference to a UErrorCode to receive any errors. |
| U_CAPI UText * uregex_getUText | ( | URegularExpression * | regexp, |
| UText * | dest, | ||
| UErrorCode * | status | ||
| ) |
Get the subject text that is currently associated with this regular expression object.
This function will work even if the input was originally specified as a UChar string.
| regexp | The compiled regular expression. |
| dest | A mutable UText in which to store the current input. If NULL, a new UText will be created as an immutable shallow clone of the actual input string. |
| status | Receives errors detected by this function. |
| U_CAPI int32_t uregex_group | ( | URegularExpression * | regexp, |
| int32_t | groupNum, | ||
| UChar * | dest, | ||
| int32_t | destCapacity, | ||
| UErrorCode * | status | ||
| ) |
Extract the string for the specified matching expression or subexpression.
Group #0 is the complete string of matched text. Group #1 is the text matched by the first set of capturing parentheses.
| regexp | The compiled regular expression. |
| groupNum | The capture group to extract. Group 0 is the complete match. The value of this parameter must be less than or equal to the number of capture groups in the pattern. |
| dest | Buffer to receive the matching string data |
| destCapacity | Capacity of the dest buffer. |
| status | A reference to a UErrorCode to receive any errors. |
| U_CAPI int32_t uregex_groupCount | ( | URegularExpression * | regexp, |
| UErrorCode * | status | ||
| ) |
Get the number of capturing groups in this regular expression's pattern.
| regexp | The compiled regular expression. |
| status | A reference to a UErrorCode to receive any errors. |
| U_CAPI int32_t uregex_groupNumberFromCName | ( | URegularExpression * | regexp, |
| const char * | groupName, | ||
| int32_t | nameLength, | ||
| UErrorCode * | status | ||
| ) |
Get the group number corresponding to a named capture group.
The returned number can be used with any function that access capture groups by number.
The function returns an error status if the specified name does not appear in the pattern.
| regexp | The compiled regular expression. |
| groupName | The capture group name, platform invariant characters only. |
| nameLength | The length of the name, or -1 if the name is nul-terminated. |
| status | A pointer to a UErrorCode to receive any errors. |
| U_CAPI int32_t uregex_groupNumberFromName | ( | URegularExpression * | regexp, |
| const UChar * | groupName, | ||
| int32_t | nameLength, | ||
| UErrorCode * | status | ||
| ) |
Get the group number corresponding to a named capture group.
The returned number can be used with any function that access capture groups by number.
The function returns an error status if the specified name does not appear in the pattern.
| regexp | The compiled regular expression. |
| groupName | The capture group name. |
| nameLength | The length of the name, or -1 if the name is a nul-terminated string. |
| status | A pointer to a UErrorCode to receive any errors. |
| U_CAPI UText * uregex_groupUText | ( | URegularExpression * | regexp, |
| int32_t | groupNum, | ||
| UText * | dest, | ||
| int64_t * | groupLength, | ||
| UErrorCode * | status | ||
| ) |
Returns a shallow immutable clone of the entire input string with the current index set to the beginning of the requested capture group.
The capture group length is also returned via groupLength. Group #0 is the complete string of matched text. Group #1 is the text matched by the first set of capturing parentheses.
| regexp | The compiled regular expression. |
| groupNum | The capture group to extract. Group 0 is the complete match. The value of this parameter must be less than or equal to the number of capture groups in the pattern. |
| dest | A mutable UText in which to store the current input. If NULL, a new UText will be created as an immutable shallow clone of the entire input string. |
| groupLength | The group length of the desired capture group. Output parameter. |
| status | A reference to a UErrorCode to receive any errors. |
| U_CAPI UBool uregex_hasAnchoringBounds | ( | const URegularExpression * | regexp, |
| UErrorCode * | status | ||
| ) |
Return true if this URegularExpression is using anchoring bounds.
By default, anchoring region bounds are used.
| regexp | The compiled regular expression. |
| status | A pointer to a UErrorCode to receive any errors. |
| U_CAPI UBool uregex_hasTransparentBounds | ( | const URegularExpression * | regexp, |
| UErrorCode * | status | ||
| ) |
Queries the transparency of region bounds for this URegularExpression.
See useTransparentBounds for a description of transparent and opaque bounds. By default, matching boundaries are opaque.
| regexp | The compiled regular expression. |
| status | A pointer to a UErrorCode to receive any errors. |
| U_CAPI UBool uregex_hitEnd | ( | const URegularExpression * | regexp, |
| UErrorCode * | status | ||
| ) |
Return true if the most recent matching operation touched the end of the text being processed.
In this case, additional input text could change the results of that match.
| regexp | The compiled regular expression. |
| status | A pointer to a UErrorCode to receive any errors. |
| U_CAPI UBool uregex_lookingAt | ( | URegularExpression * | regexp, |
| int32_t | startIndex, | ||
| UErrorCode * | status | ||
| ) |
Attempts to match the input string, starting from the specified index, against the pattern.
The match may be of any length, and is not required to extend to the end of the input string. Contrast with uregex_matches().
If startIndex is >= 0 any input region that was set for this URegularExpression is reset before the operation begins.
If the specified starting index == -1 the match begins at the start of the input region, or at the start of the full string if no region has been specified. This corresponds directly with Matcher.lookingAt() in Java.
If the match succeeds then more information can be obtained via the uregexp_start(), uregexp_end(), and uregex_group() functions.
| regexp | The compiled regular expression. |
| startIndex | The input string (native) index at which to begin matching, or -1 to match the Input Region |
| status | A reference to a UErrorCode to receive any errors. |
| U_CAPI UBool uregex_lookingAt64 | ( | URegularExpression * | regexp, |
| int64_t | startIndex, | ||
| UErrorCode * | status | ||
| ) |
64bit version of uregex_lookingAt.
Attempts to match the input string, starting from the specified index, against the pattern. The match may be of any length, and is not required to extend to the end of the input string. Contrast with uregex_matches().
If startIndex is >= 0 any input region that was set for this URegularExpression is reset before the operation begins.
If the specified starting index == -1 the match begins at the start of the input region, or at the start of the full string if no region has been specified. This corresponds directly with Matcher.lookingAt() in Java.
If the match succeeds then more information can be obtained via the uregexp_start(), uregexp_end(), and uregex_group() functions.
| regexp | The compiled regular expression. |
| startIndex | The input string (native) index at which to begin matching, or -1 to match the Input Region |
| status | A reference to a UErrorCode to receive any errors. |
| U_CAPI UBool uregex_matches | ( | URegularExpression * | regexp, |
| int32_t | startIndex, | ||
| UErrorCode * | status | ||
| ) |
Attempts to match the input string against the pattern.
To succeed, the match must extend to the end of the string, or cover the complete match region.
If startIndex >= zero the match operation starts at the specified index and must extend to the end of the input string. Any region that has been specified is reset.
If startIndex == -1 the match must cover the input region, or the entire input string if no region has been set. This directly corresponds to Matcher.matches() in Java
| regexp | The compiled regular expression. |
| startIndex | The input string (native) index at which to begin matching, or -1 to match the input Region. |
| status | Receives errors detected by this function. |
| U_CAPI UBool uregex_matches64 | ( | URegularExpression * | regexp, |
| int64_t | startIndex, | ||
| UErrorCode * | status | ||
| ) |
64bit version of uregex_matches.
Attempts to match the input string against the pattern. To succeed, the match must extend to the end of the string, or cover the complete match region.
If startIndex >= zero the match operation starts at the specified index and must extend to the end of the input string. Any region that has been specified is reset.
If startIndex == -1 the match must cover the input region, or the entire input string if no region has been set. This directly corresponds to Matcher.matches() in Java
| regexp | The compiled regular expression. |
| startIndex | The input string (native) index at which to begin matching, or -1 to match the input Region. |
| status | Receives errors detected by this function. |
| U_CAPI URegularExpression * uregex_open | ( | const UChar * | pattern, |
| int32_t | patternLength, | ||
| uint32_t | flags, | ||
| UParseError * | pe, | ||
| UErrorCode * | status | ||
| ) |
Open (compile) an ICU regular expression.
Compiles the regular expression in string form into an internal representation using the specified match mode flags. The resulting regular expression handle can then be used to perform various matching operations.
| pattern | The Regular Expression pattern to be compiled. |
| patternLength | The length of the pattern, or -1 if the pattern is NUL terminated. |
| flags | Flags that alter the default matching behavior for the regular expression, UREGEX_CASE_INSENSITIVE, for example. For default behavior, set this parameter to zero. See enum URegexpFlag. All desired flags are bitwise-ORed together. |
| pe | Receives the position (line and column numbers) of any syntax error within the source regular expression string. If this information is not wanted, pass NULL for this parameter. |
| status | Receives error detected by this function. |
| U_CAPI URegularExpression * uregex_openC | ( | const char * | pattern, |
| uint32_t | flags, | ||
| UParseError * | pe, | ||
| UErrorCode * | status | ||
| ) |
Open (compile) an ICU regular expression.
The resulting regular expression handle can then be used to perform various matching operations.
This function is the same as uregex_open, except that the pattern is supplied as an 8 bit char * string in the default code page.
| pattern | The Regular Expression pattern to be compiled, NUL terminated. |
| flags | Flags that alter the default matching behavior for the regular expression, UREGEX_CASE_INSENSITIVE, for example. For default behavior, set this parameter to zero. See enum URegexpFlag. All desired flags are bitwise-ORed together. |
| pe | Receives the position (line and column numbers) of any syntax error within the source regular expression string. If this information is not wanted, pass NULL for this parameter. |
| status | Receives errors detected by this function. |
| U_CAPI URegularExpression * uregex_openUText | ( | UText * | pattern, |
| uint32_t | flags, | ||
| UParseError * | pe, | ||
| UErrorCode * | status | ||
| ) |
Open (compile) an ICU regular expression.
Compiles the regular expression in string form into an internal representation using the specified match mode flags. The resulting regular expression handle can then be used to perform various matching operations.
The contents of the pattern UText will be extracted and saved. Ownership of the UText struct itself remains with the caller. This is to match the behavior of uregex_open().
| pattern | The Regular Expression pattern to be compiled. |
| flags | Flags that alter the default matching behavior for the regular expression, UREGEX_CASE_INSENSITIVE, for example. For default behavior, set this parameter to zero. See enum URegexpFlag. All desired flags are bitwise-ORed together. |
| pe | Receives the position (line and column numbers) of any syntax error within the source regular expression string. If this information is not wanted, pass NULL for this parameter. |
| status | Receives error detected by this function. |
| U_CAPI const UChar * uregex_pattern | ( | const URegularExpression * | regexp, |
| int32_t * | patLength, | ||
| UErrorCode * | status | ||
| ) |
Returns a pointer to the source form of the pattern for this regular expression.
This function will work even if the pattern was originally specified as a UText.
| regexp | The compiled regular expression. |
| patLength | This output parameter will be set to the length of the pattern string. A NULL pointer may be used here if the pattern length is not needed, as would be the case if the pattern is known in advance to be a NUL terminated string. |
| status | Receives errors detected by this function. |
| U_CAPI UText * uregex_patternUText | ( | const URegularExpression * | regexp, |
| UErrorCode * | status | ||
| ) |
Returns the source text of the pattern for this regular expression.
This function will work even if the pattern was originally specified as a UChar string.
| regexp | The compiled regular expression. |
| status | Receives errors detected by this function. |
| U_CAPI void uregex_refreshUText | ( | URegularExpression * | regexp, |
| UText * | text, | ||
| UErrorCode * | status | ||
| ) |
Set the subject text string upon which the regular expression is looking for matches without changing any other aspect of the matching state.
The new and previous text strings must have the same content.
This function is intended for use in environments where ICU is operating on strings that may move around in memory. It provides a mechanism for notifying ICU that the string has been relocated, and providing a new UText to access the string in its new position.
Note that the regular expression implementation never copies the underlying text of a string being matched, but always operates directly on the original text provided by the user. Refreshing simply drops the references to the old text and replaces them with references to the new.
Caution: this function is normally used only by very specialized system-level code. One example use case is with garbage collection that moves the text in memory.
| regexp | The compiled regular expression. |
| text | The new (moved) text string. |
| status | Receives errors detected by this function. |
| U_CAPI int32_t uregex_regionEnd | ( | const URegularExpression * | regexp, |
| UErrorCode * | status | ||
| ) |
Reports the end index (exclusive) of the matching region for this URegularExpression.
Any matches found are limited to to the region bounded by regionStart (inclusive) and regionEnd (exclusive).
| regexp | The compiled regular expression. |
| status | A pointer to a UErrorCode to receive any errors. |
| U_CAPI int64_t uregex_regionEnd64 | ( | const URegularExpression * | regexp, |
| UErrorCode * | status | ||
| ) |
64bit version of uregex_regionEnd.
Reports the end index (exclusive) of the matching region for this URegularExpression. Any matches found are limited to to the region bounded by regionStart (inclusive) and regionEnd (exclusive).
| regexp | The compiled regular expression. |
| status | A pointer to a UErrorCode to receive any errors. |
| U_CAPI int32_t uregex_regionStart | ( | const URegularExpression * | regexp, |
| UErrorCode * | status | ||
| ) |
Reports the start index of the matching region.
Any matches found are limited to to the region bounded by regionStart (inclusive) and regionEnd (exclusive).
| regexp | The compiled regular expression. |
| status | A pointer to a UErrorCode to receive any errors. |
| U_CAPI int64_t uregex_regionStart64 | ( | const URegularExpression * | regexp, |
| UErrorCode * | status | ||
| ) |
64bit version of uregex_regionStart.
Reports the start index of the matching region. Any matches found are limited to to the region bounded by regionStart (inclusive) and regionEnd (exclusive).
| regexp | The compiled regular expression. |
| status | A pointer to a UErrorCode to receive any errors. |
| U_CAPI int32_t uregex_replaceAll | ( | URegularExpression * | regexp, |
| const UChar * | replacementText, | ||
| int32_t | replacementLength, | ||
| UChar * | destBuf, | ||
| int32_t | destCapacity, | ||
| UErrorCode * | status | ||
| ) |
Replaces every substring of the input that matches the pattern with the given replacement string.
This is a convenience function that provides a complete find-and-replace-all operation.
This method scans the input string looking for matches of the pattern. Input that is not part of any match is copied unchanged to the destination buffer. Matched regions are replaced in the output buffer by the replacement string. The replacement string may contain references to capture groups; these take the form of $1, $2, etc.
| regexp | The compiled regular expression. |
| replacementText | A string containing the replacement text. |
| replacementLength | The length of the replacement string, or -1 if it is NUL terminated. |
| destBuf | A (UChar *) buffer that will receive the result. |
| destCapacity | The capacity of the destination buffer. |
| status | A reference to a UErrorCode to receive any errors. |
| U_CAPI UText * uregex_replaceAllUText | ( | URegularExpression * | regexp, |
| UText * | replacement, | ||
| UText * | dest, | ||
| UErrorCode * | status | ||
| ) |
Replaces every substring of the input that matches the pattern with the given replacement string.
This is a convenience function that provides a complete find-and-replace-all operation.
This method scans the input string looking for matches of the pattern. Input that is not part of any match is copied unchanged to the destination buffer. Matched regions are replaced in the output buffer by the replacement string. The replacement string may contain references to capture groups; these take the form of $1, $2, etc.
| regexp | The compiled regular expression. |
| replacement | A string containing the replacement text. |
| dest | A mutable UText that will receive the result. If NULL, a new UText will be created (which may not be mutable). |
| status | A reference to a UErrorCode to receive any errors. |
| U_CAPI int32_t uregex_replaceFirst | ( | URegularExpression * | regexp, |
| const UChar * | replacementText, | ||
| int32_t | replacementLength, | ||
| UChar * | destBuf, | ||
| int32_t | destCapacity, | ||
| UErrorCode * | status | ||
| ) |
Replaces the first substring of the input that matches the pattern with the given replacement string.
This is a convenience function that provides a complete find-and-replace operation.
This method scans the input string looking for a match of the pattern. All input that is not part of the match is copied unchanged to the destination buffer. The matched region is replaced in the output buffer by the replacement string. The replacement string may contain references to capture groups; these take the form of $1, $2, etc.
| regexp | The compiled regular expression. |
| replacementText | A string containing the replacement text. |
| replacementLength | The length of the replacement string, or -1 if it is NUL terminated. |
| destBuf | A (UChar *) buffer that will receive the result. |
| destCapacity | The capacity of the destination buffer. |
| status | a reference to a UErrorCode to receive any errors. |
| U_CAPI UText * uregex_replaceFirstUText | ( | URegularExpression * | regexp, |
| UText * | replacement, | ||
| UText * | dest, | ||
| UErrorCode * | status | ||
| ) |
Replaces the first substring of the input that matches the pattern with the given replacement string.
This is a convenience function that provides a complete find-and-replace operation.
This method scans the input string looking for a match of the pattern. All input that is not part of the match is copied unchanged to the destination buffer. The matched region is replaced in the output buffer by the replacement string. The replacement string may contain references to capture groups; these take the form of $1, $2, etc.
| regexp | The compiled regular expression. |
| replacement | A string containing the replacement text. |
| dest | A mutable UText that will receive the result. If NULL, a new UText will be created (which may not be mutable). |
| status | A reference to a UErrorCode to receive any errors. |
| U_CAPI UBool uregex_requireEnd | ( | const URegularExpression * | regexp, |
| UErrorCode * | status | ||
| ) |
Return true the most recent match succeeded and additional input could cause it to fail.
If this function returns false and a match was found, then more input might change the match but the match won't be lost. If a match was not found, then requireEnd has no meaning.
| regexp | The compiled regular expression. |
| status | A pointer to a UErrorCode to receive any errors. |
| U_CAPI void uregex_reset | ( | URegularExpression * | regexp, |
| int32_t | index, | ||
| UErrorCode * | status | ||
| ) |
Reset any saved state from the previous match.
Has the effect of causing uregex_findNext to begin at the specified index, and causing uregex_start(), uregex_end() and uregex_group() to return an error indicating that there is no match information available. Clears any match region that may have been set.
| regexp | The compiled regular expression. |
| index | The position (native) in the text at which a uregex_findNext() should begin searching. |
| status | A reference to a UErrorCode to receive any errors. |
| U_CAPI void uregex_reset64 | ( | URegularExpression * | regexp, |
| int64_t | index, | ||
| UErrorCode * | status | ||
| ) |
64bit version of uregex_reset.
Reset any saved state from the previous match. Has the effect of causing uregex_findNext to begin at the specified index, and causing uregex_start(), uregex_end() and uregex_group() to return an error indicating that there is no match information available. Clears any match region that may have been set.
| regexp | The compiled regular expression. |
| index | The position (native) in the text at which a uregex_findNext() should begin searching. |
| status | A reference to a UErrorCode to receive any errors. |
| U_CAPI void uregex_setFindProgressCallback | ( | URegularExpression * | regexp, |
| URegexFindProgressCallback * | callback, | ||
| const void * | context, | ||
| UErrorCode * | status | ||
| ) |
Set the find progress callback function for this URegularExpression.
| regexp | The compiled regular expression. |
| callback | A pointer to the user-supplied callback function. |
| context | User context pointer. The value supplied at the time the callback function is set will be saved and passed to the callback each time that it is called. |
| status | A reference to a UErrorCode to receive any errors. |
| U_CAPI void uregex_setMatchCallback | ( | URegularExpression * | regexp, |
| URegexMatchCallback * | callback, | ||
| const void * | context, | ||
| UErrorCode * | status | ||
| ) |
Set a callback function for this URegularExpression.
During matching operations the function will be called periodically, giving the application the opportunity to terminate a long-running match.
| regexp | The compiled regular expression. |
| callback | A pointer to the user-supplied callback function. |
| context | User context pointer. The value supplied at the time the callback function is set will be saved and passed to the callback each time that it is called. |
| status | A reference to a UErrorCode to receive any errors. |
| U_CAPI void uregex_setRegion | ( | URegularExpression * | regexp, |
| int32_t | regionStart, | ||
| int32_t | regionLimit, | ||
| UErrorCode * | status | ||
| ) |
Sets the limits of the matching region for this URegularExpression.
The region is the part of the input string that will be considered when matching. Invoking this method resets any saved state from the previous match, then sets the region to start at the index specified by the start parameter and end at the index specified by the end parameter.
Depending on the transparency and anchoring being used (see useTransparentBounds and useAnchoringBounds), certain constructs such as anchors may behave differently at or around the boundaries of the region
The function will fail if start is greater than limit, or if either index is less than zero or greater than the length of the string being matched.
| regexp | The compiled regular expression. |
| regionStart | The (native) index to begin searches at. |
| regionLimit | The (native) index to end searches at (exclusive). |
| status | A pointer to a UErrorCode to receive any errors. |
| U_CAPI void uregex_setRegion64 | ( | URegularExpression * | regexp, |
| int64_t | regionStart, | ||
| int64_t | regionLimit, | ||
| UErrorCode * | status | ||
| ) |
64bit version of uregex_setRegion.
Sets the limits of the matching region for this URegularExpression. The region is the part of the input string that will be considered when matching. Invoking this method resets any saved state from the previous match, then sets the region to start at the index specified by the start parameter and end at the index specified by the end parameter.
Depending on the transparency and anchoring being used (see useTransparentBounds and useAnchoringBounds), certain constructs such as anchors may behave differently at or around the boundaries of the region
The function will fail if start is greater than limit, or if either index is less than zero or greater than the length of the string being matched.
| regexp | The compiled regular expression. |
| regionStart | The (native) index to begin searches at. |
| regionLimit | The (native) index to end searches at (exclusive). |
| status | A pointer to a UErrorCode to receive any errors. |
| U_CAPI void uregex_setRegionAndStart | ( | URegularExpression * | regexp, |
| int64_t | regionStart, | ||
| int64_t | regionLimit, | ||
| int64_t | startIndex, | ||
| UErrorCode * | status | ||
| ) |
Set the matching region and the starting index for subsequent matches in a single operation.
This is useful because the usual function for setting the starting index, urgex_reset(), also resets any region limits.
| regexp | The compiled regular expression. |
| regionStart | The (native) index to begin searches at. |
| regionLimit | The (native) index to end searches at (exclusive). |
| startIndex | The index in the input text at which the next match operation should begin. |
| status | A pointer to a UErrorCode to receive any errors. |
| U_CAPI void uregex_setStackLimit | ( | URegularExpression * | regexp, |
| int32_t | limit, | ||
| UErrorCode * | status | ||
| ) |
Set the amount of heap storage available for use by the match backtracking stack.
ICU uses a backtracking regular expression engine, with the backtrack stack maintained on the heap. This function sets the limit to the amount of memory that can be used for this purpose. A backtracking stack overflow will result in an error from the match operation that caused it.
A limit is desirable because a malicious or poorly designed pattern can use excessive memory, potentially crashing the process. A limit is enabled by default.
| regexp | The compiled regular expression. |
| limit | The maximum size, in bytes, of the matching backtrack stack. A value of zero means no limit. The limit must be greater than or equal to zero. |
| status | A reference to a UErrorCode to receive any errors. |
| U_CAPI void uregex_setText | ( | URegularExpression * | regexp, |
| const UChar * | text, | ||
| int32_t | textLength, | ||
| UErrorCode * | status | ||
| ) |
Set the subject text string upon which the regular expression will look for matches.
This function may be called any number of times, allowing the regular expression pattern to be applied to different strings.
Regular expression matching operations work directly on the application's string data. No copy is made. The subject string data must not be altered after calling this function until after all regular expression operations involving this string data are completed.
Zero length strings are permitted. In this case, no subsequent match operation will dereference the text string pointer.
| regexp | The compiled regular expression. |
| text | The subject text string. |
| textLength | The length of the subject text, or -1 if the string is NUL terminated. |
| status | Receives errors detected by this function. |
| U_CAPI void uregex_setTimeLimit | ( | URegularExpression * | regexp, |
| int32_t | limit, | ||
| UErrorCode * | status | ||
| ) |
Set a processing time limit for match operations with this URegularExpression.
Some patterns, when matching certain strings, can run in exponential time. For practical purposes, the match operation may appear to be in an infinite loop. When a limit is set a match operation will fail with an error if the limit is exceeded.
The units of the limit are steps of the match engine. Correspondence with actual processor time will depend on the speed of the processor and the details of the specific pattern, but will typically be on the order of milliseconds.
By default, the matching time is not limited.
| regexp | The compiled regular expression. |
| limit | The limit value, or 0 for no limit. |
| status | A reference to a UErrorCode to receive any errors. |
| U_CAPI void uregex_setUText | ( | URegularExpression * | regexp, |
| UText * | text, | ||
| UErrorCode * | status | ||
| ) |
Set the subject text string upon which the regular expression will look for matches.
This function may be called any number of times, allowing the regular expression pattern to be applied to different strings.
Regular expression matching operations work directly on the application's string data; only a shallow clone is made. The subject string data must not be altered after calling this function until after all regular expression operations involving this string data are completed.
| regexp | The compiled regular expression. |
| text | The subject text string. |
| status | Receives errors detected by this function. |
| U_CAPI int32_t uregex_split | ( | URegularExpression * | regexp, |
| UChar * | destBuf, | ||
| int32_t | destCapacity, | ||
| int32_t * | requiredCapacity, | ||
| UChar * | destFields[], | ||
| int32_t | destFieldsCapacity, | ||
| UErrorCode * | status | ||
| ) |
Split a string into fields.
Somewhat like split() from Perl. The pattern matches identify delimiters that separate the input into fields. The input data between the matches becomes the fields themselves.
Each of the fields is copied from the input string to the destination buffer, and NUL terminated. The position of each field within the destination buffer is returned in the destFields array.
If the delimiter pattern includes capture groups, the captured text will also appear in the destination array of output strings, interspersed with the fields. This is similar to Perl, but differs from Java, which ignores the presence of capture groups in the pattern.
Trailing empty fields will always be returned, assuming sufficient destination capacity. This differs from the default behavior for Java and Perl where trailing empty fields are not returned.
The number of strings produced by the split operation is returned. This count includes the strings from capture groups in the delimiter pattern. This behavior differs from Java, which ignores capture groups.
| regexp | The compiled regular expression. |
| destBuf | A (UChar *) buffer to receive the fields that are extracted from the input string. These field pointers will refer to positions within the destination buffer supplied by the caller. Any extra positions within the destFields array will be set to NULL. |
| destCapacity | The capacity of the destBuf. |
| requiredCapacity | The actual capacity required of the destBuf. If destCapacity is too small, requiredCapacity will return the total capacity required to hold all of the output, and a U_BUFFER_OVERFLOW_ERROR will be returned. |
| destFields | An array to be filled with the position of each of the extracted fields within destBuf. |
| destFieldsCapacity | The number of elements in the destFields array. If the number of fields found is less than destFieldsCapacity, the extra destFields elements are set to zero. If destFieldsCapacity is too small, the trailing part of the input, including any field delimiters, is treated as if it were the last field - it is copied to the destBuf, and its position is in the destBuf is stored in the last element of destFields. This behavior mimics that of Perl. It is not an error condition, and no error status is returned when all destField positions are used. |
| status | A reference to a UErrorCode to receive any errors. |
| U_CAPI int32_t uregex_splitUText | ( | URegularExpression * | regexp, |
| UText * | destFields[], | ||
| int32_t | destFieldsCapacity, | ||
| UErrorCode * | status | ||
| ) |
Split a string into fields.
Somewhat like split() from Perl. The pattern matches identify delimiters that separate the input into fields. The input data between the matches becomes the fields themselves.
The behavior of this function is not very closely aligned with uregex_split(); instead, it is based on (and implemented directly on top of) the C++ split method.
| regexp | The compiled regular expression. |
| destFields | An array of mutable UText structs to receive the results of the split. If a field is NULL, a new UText is allocated to contain the results for that field. This new UText is not guaranteed to be mutable. |
| destFieldsCapacity | The number of elements in the destination array. If the number of fields found is less than destCapacity, the extra strings in the destination array are not altered. If the number of destination strings is less than the number of fields, the trailing part of the input string, including any field delimiters, is placed in the last destination string. This behavior mimics that of Perl. It is not an error condition, and no error status is returned when all destField positions are used. |
| status | A reference to a UErrorCode to receive any errors. |
| U_CAPI int32_t uregex_start | ( | URegularExpression * | regexp, |
| int32_t | groupNum, | ||
| UErrorCode * | status | ||
| ) |
Returns the index in the input string of the start of the text matched by the specified capture group during the previous match operation.
Return -1 if the capture group was not part of the last match. Group #0 refers to the complete range of matched text. Group #1 refers to the text matched by the first set of capturing parentheses.
| regexp | The compiled regular expression. |
| groupNum | The capture group number |
| status | A reference to a UErrorCode to receive any errors. |
| U_CAPI int64_t uregex_start64 | ( | URegularExpression * | regexp, |
| int32_t | groupNum, | ||
| UErrorCode * | status | ||
| ) |
64bit version of uregex_start.
Returns the index in the input string of the start of the text matched by the specified capture group during the previous match operation. Return -1 if the capture group was not part of the last match. Group #0 refers to the complete range of matched text. Group #1 refers to the text matched by the first set of capturing parentheses.
| regexp | The compiled regular expression. |
| groupNum | The capture group number |
| status | A reference to a UErrorCode to receive any errors. |
| U_CAPI void uregex_useAnchoringBounds | ( | URegularExpression * | regexp, |
| UBool | b, | ||
| UErrorCode * | status | ||
| ) |
Set whether this URegularExpression is using Anchoring Bounds for its region.
With anchoring bounds, pattern anchors such as ^ and $ will match at the start and end of the region. Without Anchoring Bounds, anchors will only match at the positions they would in the complete text.
Anchoring Bounds are the default for regions.
| regexp | The compiled regular expression. |
| b | true if to enable anchoring bounds; false to disable them. |
| status | A pointer to a UErrorCode to receive any errors. |
| U_CAPI void uregex_useTransparentBounds | ( | URegularExpression * | regexp, |
| UBool | b, | ||
| UErrorCode * | status | ||
| ) |
Sets the transparency of region bounds for this URegularExpression.
Invoking this function with an argument of true will set matches to use transparent bounds. If the boolean argument is false, then opaque bounds will be used.
Using transparent bounds, the boundaries of the matching region are transparent to lookahead, lookbehind, and boundary matching constructs. Those constructs can see text beyond the boundaries of the region while checking for a match.
With opaque bounds, no text outside of the matching region is visible to lookahead, lookbehind, and boundary matching constructs.
By default, opaque bounds are used.
| regexp | The compiled regular expression. |
| b | true for transparent bounds; false for opaque bounds |
| status | A pointer to a UErrorCode to receive any errors. |
1.9.8