diff options
| -rw-r--r-- | ChangeLog | 5 | ||||
| -rw-r--r-- | doc/ChangeLog | 5 | ||||
| -rw-r--r-- | doc/gawk.info | 1040 | ||||
| -rw-r--r-- | doc/gawk.texi | 9 | ||||
| -rw-r--r-- | doc/gawktexi.in | 9 | ||||
| -rw-r--r-- | regcomp.c | 32 | ||||
| -rw-r--r-- | regex.c | 2 | ||||
| -rw-r--r-- | regex.h | 2 | ||||
| -rw-r--r-- | regex_internal.c | 18 | ||||
| -rw-r--r-- | regex_internal.h | 6 | ||||
| -rw-r--r-- | regexec.c | 90 |
11 files changed, 610 insertions, 608 deletions
@@ -1,3 +1,8 @@ +2016-02-20 Arnold D. Robbins <arnold@skeeve.com> + + * regcomp.c, regex.c, regex.h, regex_internal.c, regex_internal.h, + regexec.c: Sync with GLIBC, mostly prototype changes. + 2016-02-18 Arnold D. Robbins <arnold@skeeve.com> Fix profile / pretty-printing to chain else-ifs. diff --git a/doc/ChangeLog b/doc/ChangeLog index 6017ee44..a8c33d4d 100644 --- a/doc/ChangeLog +++ b/doc/ChangeLog @@ -1,3 +1,8 @@ +2016-02-20 Arnold D. Robbins <arnold@skeeve.com> + + * gawktexilin (Bracket Expressions): Add a small note about + Unicode in bracket expressions. + 2016-02-18 Arnold D. Robbins <arnold@skeeve.com> * gawktexi.in: Fixes in wc.awk and in cut.awk. Thanks to David Ward, diff --git a/doc/gawk.info b/doc/gawk.info index 35484814..cf6a1356 100644 --- a/doc/gawk.info +++ b/doc/gawk.info @@ -3732,6 +3732,14 @@ character set. For example, '[0-9]' is equivalent to '[0123456789]'. standard and 'gawk' have changed over time. This is mainly of historical interest.) + With the increasing popularity of the Unicode character standard +(http://www.unicode.org), there is an additional wrinkle to consider. +Octal and hexadecimal escape sequences inside bracket expressions are +taken to represent only single-byte characters (characters whose values +fit within the range 0-256). To match a range of characters where the +endpoints of the range are larger than 256, enter the multibyte +encodings of the characters directly. + To include one of the characters '\', ']', '-', or '^' in a bracket expression, put a '\' in front of it. For example: @@ -32138,7 +32146,7 @@ Index * - (hyphen), -= operator: Assignment Ops. (line 129) * - (hyphen), -= operator <1>: Precedence. (line 94) * - (hyphen), filenames beginning with: Options. (line 60) -* - (hyphen), in bracket expressions: Bracket Expressions. (line 17) +* - (hyphen), in bracket expressions: Bracket Expressions. (line 25) * --assign option: Options. (line 32) * --bignum option: Options. (line 203) * --characters-as-bytes option: Options. (line 69) @@ -32293,7 +32301,7 @@ Index (line 43) * \ (backslash), gsub()/gensub()/sub() functions and: Gory Details. (line 6) -* \ (backslash), in bracket expressions: Bracket Expressions. (line 17) +* \ (backslash), in bracket expressions: Bracket Expressions. (line 25) * \ (backslash), in escape sequences: Escape Sequences. (line 6) * \ (backslash), in escape sequences <1>: Escape Sequences. (line 103) * \ (backslash), in escape sequences, POSIX and: Escape Sequences. @@ -32332,7 +32340,7 @@ Index (line 41) * \ (backslash), \` operator (gawk): GNU Regexp Operators. (line 57) -* ^ (caret), in bracket expressions: Bracket Expressions. (line 17) +* ^ (caret), in bracket expressions: Bracket Expressions. (line 25) * ^ (caret), in FS: Regexp Field Splitting. (line 59) * ^ (caret), regexp operator: Regexp Operators. (line 22) @@ -32590,7 +32598,7 @@ Index (line 43) * backslash (\), gsub()/gensub()/sub() functions and: Gory Details. (line 6) -* backslash (\), in bracket expressions: Bracket Expressions. (line 17) +* backslash (\), in bracket expressions: Bracket Expressions. (line 25) * backslash (\), in escape sequences: Escape Sequences. (line 6) * backslash (\), in escape sequences <1>: Escape Sequences. (line 103) * backslash (\), in escape sequences, POSIX and: Escape Sequences. @@ -32691,15 +32699,15 @@ Index * bracket expressions: Regexp Operators. (line 56) * bracket expressions <1>: Bracket Expressions. (line 6) * bracket expressions, character classes: Bracket Expressions. - (line 32) + (line 40) * bracket expressions, collating elements: Bracket Expressions. - (line 78) + (line 86) * bracket expressions, collating symbols: Bracket Expressions. - (line 85) + (line 93) * bracket expressions, complemented: Regexp Operators. (line 64) * bracket expressions, equivalence classes: Bracket Expressions. - (line 91) -* bracket expressions, non-ASCII: Bracket Expressions. (line 78) + (line 99) +* bracket expressions, non-ASCII: Bracket Expressions. (line 86) * bracket expressions, range expressions: Bracket Expressions. (line 6) * break debugger command: Breakpoint Control. (line 11) @@ -32764,7 +32772,7 @@ Index * call by value: Pass By Value/Reference. (line 15) * call stack, display in debugger: Execution Stack. (line 13) -* caret (^), in bracket expressions: Bracket Expressions. (line 17) +* caret (^), in bracket expressions: Bracket Expressions. (line 25) * caret (^), regexp operator: Regexp Operators. (line 22) * caret (^), regexp operator <1>: GNU Regexp Operators. (line 62) @@ -32816,8 +32824,8 @@ Index * Close, Diane: Manual History. (line 34) * Close, Diane <1>: Contributors. (line 21) * Collado, Manuel: Acknowledgments. (line 60) -* collating elements: Bracket Expressions. (line 78) -* collating symbols: Bracket Expressions. (line 85) +* collating elements: Bracket Expressions. (line 86) +* collating symbols: Bracket Expressions. (line 93) * Colombo, Antonio: Acknowledgments. (line 60) * Colombo, Antonio <1>: Contributors. (line 141) * columns, aligning: Print Examples. (line 69) @@ -33248,7 +33256,7 @@ Index * EBCDIC: Ordinal Functions. (line 45) * effective group ID of gawk user: Auto-set. (line 153) * effective user ID of gawk user: Auto-set. (line 161) -* egrep utility: Bracket Expressions. (line 26) +* egrep utility: Bracket Expressions. (line 34) * egrep utility <1>: Egrep Program. (line 6) * egrep.awk program: Egrep Program. (line 53) * elements in arrays, assigning values: Assigning Elements. (line 6) @@ -33300,7 +33308,7 @@ Index * equals sign (=), == operator: Comparison Operators. (line 11) * equals sign (=), == operator <1>: Precedence. (line 64) -* EREs (Extended Regular Expressions): Bracket Expressions. (line 26) +* EREs (Extended Regular Expressions): Bracket Expressions. (line 34) * ERRNO variable: Auto-set. (line 87) * ERRNO variable <1>: TCP/IP Networking. (line 54) * ERRNO variable, with BEGINFILE pattern: BEGINFILE/ENDFILE. (line 26) @@ -33361,7 +33369,7 @@ Index * expressions, matching, See comparison expressions: Typing and Comparison. (line 9) * expressions, selecting: Conditional Exp. (line 6) -* Extended Regular Expressions (EREs): Bracket Expressions. (line 26) +* Extended Regular Expressions (EREs): Bracket Expressions. (line 34) * extension API: Extension API Description. (line 6) * extension API informational variables: Extension API Informational Variables. @@ -33630,7 +33638,7 @@ Index * gawk, awk and <1>: This Manual. (line 14) * gawk, bitwise operations in: Bitwise Functions. (line 40) * gawk, break statement in: Break Statement. (line 51) -* gawk, character classes and: Bracket Expressions. (line 100) +* gawk, character classes and: Bracket Expressions. (line 108) * gawk, coding style in: Adding Code. (line 37) * gawk, command-line options, and regular expressions: GNU Regexp Operators. (line 73) @@ -33834,7 +33842,7 @@ Index * hyphen (-), -= operator: Assignment Ops. (line 129) * hyphen (-), -= operator <1>: Precedence. (line 94) * hyphen (-), filenames beginning with: Options. (line 60) -* hyphen (-), in bracket expressions: Bracket Expressions. (line 17) +* hyphen (-), in bracket expressions: Bracket Expressions. (line 25) * i debugger command (alias for info): Debugger Info. (line 13) * id utility: Id Program. (line 6) * id.awk program: Id Program. (line 31) @@ -33923,7 +33931,7 @@ Index * internationalization, localization <1>: Internationalization. (line 13) * internationalization, localization, character classes: Bracket Expressions. - (line 100) + (line 108) * internationalization, localization, gawk and: Internationalization. (line 13) * internationalization, localization, locale categories: Explaining gettext. @@ -34386,11 +34394,11 @@ Index * POSIX awk, backslashes in string constants: Escape Sequences. (line 108) * POSIX awk, BEGIN/END patterns: I/O And BEGIN/END. (line 15) -* POSIX awk, bracket expressions and: Bracket Expressions. (line 26) +* POSIX awk, bracket expressions and: Bracket Expressions. (line 34) * POSIX awk, bracket expressions and, character classes: Bracket Expressions. - (line 32) + (line 40) * POSIX awk, bracket expressions and, character classes <1>: Bracket Expressions. - (line 100) + (line 108) * POSIX awk, break statement and: Break Statement. (line 51) * POSIX awk, changes in awk versions: POSIX. (line 6) * POSIX awk, continue statement and: Continue Statement. (line 44) @@ -35254,500 +35262,500 @@ Node: Regexp Operators164120 Ref: Regexp Operators-Footnote-1171536 Ref: Regexp Operators-Footnote-2171683 Node: Bracket Expressions171781 -Ref: table-char-classes173803 -Node: Leftmost Longest176940 -Node: Computed Regexps178243 -Node: GNU Regexp Operators181670 -Node: Case-sensitivity185349 -Ref: Case-sensitivity-Footnote-1188245 -Ref: Case-sensitivity-Footnote-2188480 -Node: Strong Regexp Constants188588 -Node: Regexp Summary191530 -Node: Reading Files193136 -Node: Records195299 -Node: awk split records196032 -Node: gawk split records200963 -Ref: gawk split records-Footnote-1205503 -Node: Fields205540 -Node: Nonconstant Fields208281 -Ref: Nonconstant Fields-Footnote-1210517 -Node: Changing Fields210721 -Node: Field Separators216649 -Node: Default Field Splitting219347 -Node: Regexp Field Splitting220465 -Node: Single Character Fields223818 -Node: Command Line Field Separator224878 -Node: Full Line Fields228096 -Ref: Full Line Fields-Footnote-1229618 -Ref: Full Line Fields-Footnote-2229664 -Node: Field Splitting Summary229765 -Node: Constant Size231839 -Node: Splitting By Content236417 -Ref: Splitting By Content-Footnote-1240388 -Node: Multiple Line240551 -Ref: Multiple Line-Footnote-1246433 -Node: Getline246612 -Node: Plain Getline249078 -Node: Getline/Variable251717 -Node: Getline/File252866 -Node: Getline/Variable/File254252 -Ref: Getline/Variable/File-Footnote-1255855 -Node: Getline/Pipe255943 -Node: Getline/Variable/Pipe258648 -Node: Getline/Coprocess259781 -Node: Getline/Variable/Coprocess261046 -Node: Getline Notes261786 -Node: Getline Summary264581 -Ref: table-getline-variants265003 -Node: Read Timeout265751 -Ref: Read Timeout-Footnote-1269657 -Node: Retrying Input269715 -Node: Command-line directories270914 -Node: Input Summary271820 -Node: Input Exercises274992 -Node: Printing275720 -Node: Print277554 -Node: Print Examples279011 -Node: Output Separators281791 -Node: OFMT283808 -Node: Printf285164 -Node: Basic Printf285949 -Node: Control Letters287523 -Node: Format Modifiers291511 -Node: Printf Examples297526 -Node: Redirection300012 -Node: Special FD306853 -Ref: Special FD-Footnote-1310021 -Node: Special Files310095 -Node: Other Inherited Files310712 -Node: Special Network311713 -Node: Special Caveats312573 -Node: Close Files And Pipes313522 -Ref: Close Files And Pipes-Footnote-1320709 -Ref: Close Files And Pipes-Footnote-2320857 -Node: Nonfatal321008 -Node: Output Summary323333 -Node: Output Exercises324555 -Node: Expressions325234 -Node: Values326422 -Node: Constants327100 -Node: Scalar Constants327791 -Ref: Scalar Constants-Footnote-1328655 -Node: Nondecimal-numbers328905 -Node: Regexp Constants331918 -Node: Using Constant Regexps332444 -Node: Variables335607 -Node: Using Variables336264 -Node: Assignment Options338174 -Node: Conversion340047 -Node: Strings And Numbers340571 -Ref: Strings And Numbers-Footnote-1343634 -Node: Locale influences conversions343743 -Ref: table-locale-affects346501 -Node: All Operators347119 -Node: Arithmetic Ops347748 -Node: Concatenation350254 -Ref: Concatenation-Footnote-1353101 -Node: Assignment Ops353208 -Ref: table-assign-ops358199 -Node: Increment Ops359512 -Node: Truth Values and Conditions362972 -Node: Truth Values364046 -Node: Typing and Comparison365094 -Node: Variable Typing365914 -Node: Comparison Operators369538 -Ref: table-relational-ops369957 -Node: POSIX String Comparison373452 -Ref: POSIX String Comparison-Footnote-1374526 -Node: Boolean Ops374665 -Ref: Boolean Ops-Footnote-1379147 -Node: Conditional Exp379239 -Node: Function Calls380975 -Node: Precedence384852 -Node: Locales388511 -Node: Expressions Summary390143 -Node: Patterns and Actions392716 -Node: Pattern Overview393836 -Node: Regexp Patterns395513 -Node: Expression Patterns396055 -Node: Ranges399836 -Node: BEGIN/END402944 -Node: Using BEGIN/END403705 -Ref: Using BEGIN/END-Footnote-1406441 -Node: I/O And BEGIN/END406547 -Node: BEGINFILE/ENDFILE408861 -Node: Empty411768 -Node: Using Shell Variables412085 -Node: Action Overview414359 -Node: Statements416684 -Node: If Statement418532 -Node: While Statement420027 -Node: Do Statement422055 -Node: For Statement423203 -Node: Switch Statement426361 -Node: Break Statement428747 -Node: Continue Statement430839 -Node: Next Statement432666 -Node: Nextfile Statement435049 -Node: Exit Statement437701 -Node: Built-in Variables440104 -Node: User-modified441237 -Node: Auto-set448823 -Ref: Auto-set-Footnote-1463210 -Ref: Auto-set-Footnote-2463416 -Node: ARGC and ARGV463472 -Node: Pattern Action Summary467685 -Node: Arrays470115 -Node: Array Basics471444 -Node: Array Intro472288 -Ref: figure-array-elements474263 -Ref: Array Intro-Footnote-1476967 -Node: Reference to Elements477095 -Node: Assigning Elements479559 -Node: Array Example480050 -Node: Scanning an Array481809 -Node: Controlling Scanning484831 -Ref: Controlling Scanning-Footnote-1490230 -Node: Numeric Array Subscripts490546 -Node: Uninitialized Subscripts492730 -Node: Delete494349 -Ref: Delete-Footnote-1497101 -Node: Multidimensional497158 -Node: Multiscanning500253 -Node: Arrays of Arrays501844 -Node: Arrays Summary506611 -Node: Functions508704 -Node: Built-in509742 -Node: Calling Built-in510820 -Node: Numeric Functions512816 -Ref: Numeric Functions-Footnote-1517649 -Ref: Numeric Functions-Footnote-2518006 -Ref: Numeric Functions-Footnote-3518054 -Node: String Functions518326 -Ref: String Functions-Footnote-1541830 -Ref: String Functions-Footnote-2541958 -Ref: String Functions-Footnote-3542206 -Node: Gory Details542293 -Ref: table-sub-escapes544084 -Ref: table-sub-proposed545603 -Ref: table-posix-sub546966 -Ref: table-gensub-escapes548507 -Ref: Gory Details-Footnote-1549330 -Node: I/O Functions549481 -Ref: I/O Functions-Footnote-1556701 -Node: Time Functions556849 -Ref: Time Functions-Footnote-1567354 -Ref: Time Functions-Footnote-2567422 -Ref: Time Functions-Footnote-3567580 -Ref: Time Functions-Footnote-4567691 -Ref: Time Functions-Footnote-5567803 -Ref: Time Functions-Footnote-6568030 -Node: Bitwise Functions568296 -Ref: table-bitwise-ops568890 -Ref: Bitwise Functions-Footnote-1573228 -Node: Type Functions573401 -Node: I18N Functions576062 -Node: User-defined577713 -Node: Definition Syntax578518 -Ref: Definition Syntax-Footnote-1584205 -Node: Function Example584276 -Ref: Function Example-Footnote-1587198 -Node: Function Caveats587220 -Node: Calling A Function587738 -Node: Variable Scope588696 -Node: Pass By Value/Reference591690 -Node: Return Statement595189 -Node: Dynamic Typing598168 -Node: Indirect Calls599098 -Ref: Indirect Calls-Footnote-1609349 -Node: Functions Summary609477 -Node: Library Functions612182 -Ref: Library Functions-Footnote-1615789 -Ref: Library Functions-Footnote-2615932 -Node: Library Names616103 -Ref: Library Names-Footnote-1619563 -Ref: Library Names-Footnote-2619786 -Node: General Functions619872 -Node: Strtonum Function620975 -Node: Assert Function623997 -Node: Round Function627323 -Node: Cliff Random Function628864 -Node: Ordinal Functions629880 -Ref: Ordinal Functions-Footnote-1632943 -Ref: Ordinal Functions-Footnote-2633195 -Node: Join Function633405 -Ref: Join Function-Footnote-1635175 -Node: Getlocaltime Function635375 -Node: Readfile Function639117 -Node: Shell Quoting641089 -Node: Data File Management642490 -Node: Filetrans Function643122 -Node: Rewind Function647218 -Node: File Checking649123 -Ref: File Checking-Footnote-1650457 -Node: Empty Files650658 -Node: Ignoring Assigns652637 -Node: Getopt Function654187 -Ref: Getopt Function-Footnote-1665656 -Node: Passwd Functions665856 -Ref: Passwd Functions-Footnote-1674695 -Node: Group Functions674783 -Ref: Group Functions-Footnote-1682680 -Node: Walking Arrays682887 -Node: Library Functions Summary685895 -Node: Library Exercises687301 -Node: Sample Programs687766 -Node: Running Examples688536 -Node: Clones689264 -Node: Cut Program690488 -Node: Egrep Program700417 -Ref: Egrep Program-Footnote-1707929 -Node: Id Program708039 -Node: Split Program711719 -Ref: Split Program-Footnote-1715178 -Node: Tee Program715307 -Node: Uniq Program718097 -Node: Wc Program725523 -Ref: Wc Program-Footnote-1729778 -Node: Miscellaneous Programs729872 -Node: Dupword Program731085 -Node: Alarm Program733115 -Node: Translate Program737970 -Ref: Translate Program-Footnote-1742535 -Node: Labels Program742805 -Ref: Labels Program-Footnote-1746156 -Node: Word Sorting746240 -Node: History Sorting750312 -Node: Extract Program752147 -Node: Simple Sed759676 -Node: Igawk Program762750 -Ref: Igawk Program-Footnote-1777081 -Ref: Igawk Program-Footnote-2777283 -Ref: Igawk Program-Footnote-3777405 -Node: Anagram Program777520 -Node: Signature Program780582 -Node: Programs Summary781829 -Node: Programs Exercises783043 -Ref: Programs Exercises-Footnote-1787172 -Node: Advanced Features787263 -Node: Nondecimal Data789253 -Node: Array Sorting790844 -Node: Controlling Array Traversal791544 -Ref: Controlling Array Traversal-Footnote-1799911 -Node: Array Sorting Functions800029 -Ref: Array Sorting Functions-Footnote-1805120 -Node: Two-way I/O805316 -Ref: Two-way I/O-Footnote-1811136 -Ref: Two-way I/O-Footnote-2811323 -Node: TCP/IP Networking811405 -Node: Profiling814523 -Node: Advanced Features Summary822977 -Node: Internationalization824821 -Node: I18N and L10N826301 -Node: Explaining gettext826988 -Ref: Explaining gettext-Footnote-1832011 -Ref: Explaining gettext-Footnote-2832196 -Node: Programmer i18n832361 -Ref: Programmer i18n-Footnote-1837216 -Node: Translator i18n837265 -Node: String Extraction838059 -Ref: String Extraction-Footnote-1839191 -Node: Printf Ordering839277 -Ref: Printf Ordering-Footnote-1842063 -Node: I18N Portability842127 -Ref: I18N Portability-Footnote-1844583 -Node: I18N Example844646 -Ref: I18N Example-Footnote-1847452 -Node: Gawk I18N847525 -Node: I18N Summary848170 -Node: Debugger849511 -Node: Debugging850533 -Node: Debugging Concepts850974 -Node: Debugging Terms852783 -Node: Awk Debugging855358 -Node: Sample Debugging Session856264 -Node: Debugger Invocation856798 -Node: Finding The Bug858184 -Node: List of Debugger Commands864662 -Node: Breakpoint Control865995 -Node: Debugger Execution Control869689 -Node: Viewing And Changing Data873051 -Node: Execution Stack876425 -Node: Debugger Info878062 -Node: Miscellaneous Debugger Commands882133 -Node: Readline Support887221 -Node: Limitations888117 -Ref: Limitations-Footnote-1892348 -Node: Debugging Summary892399 -Node: Arbitrary Precision Arithmetic893678 -Node: Computer Arithmetic895094 -Ref: table-numeric-ranges898685 -Ref: Computer Arithmetic-Footnote-1899407 -Node: Math Definitions899464 -Ref: table-ieee-formats902778 -Ref: Math Definitions-Footnote-1903381 -Node: MPFR features903486 -Node: FP Math Caution905203 -Ref: FP Math Caution-Footnote-1906275 -Node: Inexactness of computations906644 -Node: Inexact representation907604 -Node: Comparing FP Values908964 -Node: Errors accumulate910046 -Node: Getting Accuracy911479 -Node: Try To Round914189 -Node: Setting precision915088 -Ref: table-predefined-precision-strings915785 -Node: Setting the rounding mode917615 -Ref: table-gawk-rounding-modes917989 -Ref: Setting the rounding mode-Footnote-1921397 -Node: Arbitrary Precision Integers921576 -Ref: Arbitrary Precision Integers-Footnote-1926493 -Node: POSIX Floating Point Problems926642 -Ref: POSIX Floating Point Problems-Footnote-1930524 -Node: Floating point summary930562 -Node: Dynamic Extensions932752 -Node: Extension Intro934305 -Node: Plugin License935571 -Node: Extension Mechanism Outline936368 -Ref: figure-load-extension936807 -Ref: figure-register-new-function938372 -Ref: figure-call-new-function939464 -Node: Extension API Description941526 -Node: Extension API Functions Introduction943058 -Node: General Data Types947917 -Ref: General Data Types-Footnote-1953872 -Node: Memory Allocation Functions954171 -Ref: Memory Allocation Functions-Footnote-1957016 -Node: Constructor Functions957115 -Node: Registration Functions958860 -Node: Extension Functions959545 -Node: Exit Callback Functions961844 -Node: Extension Version String963094 -Node: Input Parsers963757 -Node: Output Wrappers973642 -Node: Two-way processors978154 -Node: Printing Messages980418 -Ref: Printing Messages-Footnote-1981492 -Node: Updating ERRNO981645 -Node: Requesting Values982384 -Ref: table-value-types-returned983121 -Node: Accessing Parameters984004 -Node: Symbol Table Access985239 -Node: Symbol table by name985751 -Node: Symbol table by cookie987772 -Ref: Symbol table by cookie-Footnote-1991921 -Node: Cached values991985 -Ref: Cached values-Footnote-1995486 -Node: Array Manipulation995577 -Ref: Array Manipulation-Footnote-1996668 -Node: Array Data Types996705 -Ref: Array Data Types-Footnote-1999363 -Node: Array Functions999455 -Node: Flattening Arrays1003313 -Node: Creating Arrays1010221 -Node: Redirection API1014992 -Node: Extension API Variables1017823 -Node: Extension Versioning1018456 -Node: Extension API Informational Variables1020347 -Node: Extension API Boilerplate1021411 -Node: Finding Extensions1025225 -Node: Extension Example1025784 -Node: Internal File Description1026582 -Node: Internal File Ops1030662 -Ref: Internal File Ops-Footnote-11042424 -Node: Using Internal File Ops1042564 -Ref: Using Internal File Ops-Footnote-11044947 -Node: Extension Samples1045221 -Node: Extension Sample File Functions1046750 -Node: Extension Sample Fnmatch1054399 -Node: Extension Sample Fork1055886 -Node: Extension Sample Inplace1057104 -Node: Extension Sample Ord1060314 -Node: Extension Sample Readdir1061150 -Ref: table-readdir-file-types1062039 -Node: Extension Sample Revout1062844 -Node: Extension Sample Rev2way1063433 -Node: Extension Sample Read write array1064173 -Node: Extension Sample Readfile1066115 -Node: Extension Sample Time1067210 -Node: Extension Sample API Tests1068558 -Node: gawkextlib1069050 -Node: Extension summary1071497 -Node: Extension Exercises1075189 -Node: Language History1076686 -Node: V7/SVR3.11078342 -Node: SVR41080494 -Node: POSIX1081928 -Node: BTL1083307 -Node: POSIX/GNU1084036 -Node: Feature History1089898 -Node: Common Extensions1104268 -Node: Ranges and Locales1105551 -Ref: Ranges and Locales-Footnote-11110167 -Ref: Ranges and Locales-Footnote-21110194 -Ref: Ranges and Locales-Footnote-31110429 -Node: Contributors1110650 -Node: History summary1116219 -Node: Installation1117599 -Node: Gawk Distribution1118543 -Node: Getting1119027 -Node: Extracting1119988 -Node: Distribution contents1121626 -Node: Unix Installation1127720 -Node: Quick Installation1128402 -Node: Shell Startup Files1130816 -Node: Additional Configuration Options1131894 -Node: Configuration Philosophy1133699 -Node: Non-Unix Installation1136068 -Node: PC Installation1136526 -Node: PC Binary Installation1137846 -Node: PC Compiling1139698 -Ref: PC Compiling-Footnote-11142722 -Node: PC Testing1142831 -Node: PC Using1144011 -Node: Cygwin1148125 -Node: MSYS1148895 -Node: VMS Installation1149396 -Node: VMS Compilation1150187 -Ref: VMS Compilation-Footnote-11151416 -Node: VMS Dynamic Extensions1151474 -Node: VMS Installation Details1153159 -Node: VMS Running1155412 -Node: VMS GNV1159691 -Node: VMS Old Gawk1160426 -Node: Bugs1160897 -Node: Other Versions1165094 -Node: Installation summary1171678 -Node: Notes1172736 -Node: Compatibility Mode1173601 -Node: Additions1174383 -Node: Accessing The Source1175308 -Node: Adding Code1176743 -Node: New Ports1182962 -Node: Derived Files1187450 -Ref: Derived Files-Footnote-11192935 -Ref: Derived Files-Footnote-21192970 -Ref: Derived Files-Footnote-31193568 -Node: Future Extensions1193682 -Node: Implementation Limitations1194340 -Node: Extension Design1195523 -Node: Old Extension Problems1196677 -Ref: Old Extension Problems-Footnote-11198195 -Node: Extension New Mechanism Goals1198252 -Ref: Extension New Mechanism Goals-Footnote-11201616 -Node: Extension Other Design Decisions1201805 -Node: Extension Future Growth1203918 -Node: Old Extension Mechanism1204754 -Node: Notes summary1206517 -Node: Basic Concepts1207699 -Node: Basic High Level1208380 -Ref: figure-general-flow1208662 -Ref: figure-process-flow1209347 -Ref: Basic High Level-Footnote-11212648 -Node: Basic Data Typing1212833 -Node: Glossary1216161 -Node: Copying1248107 -Node: GNU Free Documentation License1285646 -Node: Index1310764 +Ref: table-char-classes174257 +Node: Leftmost Longest177394 +Node: Computed Regexps178697 +Node: GNU Regexp Operators182124 +Node: Case-sensitivity185803 +Ref: Case-sensitivity-Footnote-1188699 +Ref: Case-sensitivity-Footnote-2188934 +Node: Strong Regexp Constants189042 +Node: Regexp Summary191984 +Node: Reading Files193590 +Node: Records195753 +Node: awk split records196486 +Node: gawk split records201417 +Ref: gawk split records-Footnote-1205957 +Node: Fields205994 +Node: Nonconstant Fields208735 +Ref: Nonconstant Fields-Footnote-1210971 +Node: Changing Fields211175 +Node: Field Separators217103 +Node: Default Field Splitting219801 +Node: Regexp Field Splitting220919 +Node: Single Character Fields224272 +Node: Command Line Field Separator225332 +Node: Full Line Fields228550 +Ref: Full Line Fields-Footnote-1230072 +Ref: Full Line Fields-Footnote-2230118 +Node: Field Splitting Summary230219 +Node: Constant Size232293 +Node: Splitting By Content236871 +Ref: Splitting By Content-Footnote-1240842 +Node: Multiple Line241005 +Ref: Multiple Line-Footnote-1246887 +Node: Getline247066 +Node: Plain Getline249532 +Node: Getline/Variable252171 +Node: Getline/File253320 +Node: Getline/Variable/File254706 +Ref: Getline/Variable/File-Footnote-1256309 +Node: Getline/Pipe256397 +Node: Getline/Variable/Pipe259102 +Node: Getline/Coprocess260235 +Node: Getline/Variable/Coprocess261500 +Node: Getline Notes262240 +Node: Getline Summary265035 +Ref: table-getline-variants265457 +Node: Read Timeout266205 +Ref: Read Timeout-Footnote-1270111 +Node: Retrying Input270169 +Node: Command-line directories271368 +Node: Input Summary272274 +Node: Input Exercises275446 +Node: Printing276174 +Node: Print278008 +Node: Print Examples279465 +Node: Output Separators282245 +Node: OFMT284262 +Node: Printf285618 +Node: Basic Printf286403 +Node: Control Letters287977 +Node: Format Modifiers291965 +Node: Printf Examples297980 +Node: Redirection300466 +Node: Special FD307307 +Ref: Special FD-Footnote-1310475 +Node: Special Files310549 +Node: Other Inherited Files311166 +Node: Special Network312167 +Node: Special Caveats313027 +Node: Close Files And Pipes313976 +Ref: Close Files And Pipes-Footnote-1321163 +Ref: Close Files And Pipes-Footnote-2321311 +Node: Nonfatal321462 +Node: Output Summary323787 +Node: Output Exercises325009 +Node: Expressions325688 +Node: Values326876 +Node: Constants327554 +Node: Scalar Constants328245 +Ref: Scalar Constants-Footnote-1329109 +Node: Nondecimal-numbers329359 +Node: Regexp Constants332372 +Node: Using Constant Regexps332898 +Node: Variables336061 +Node: Using Variables336718 +Node: Assignment Options338628 +Node: Conversion340501 +Node: Strings And Numbers341025 +Ref: Strings And Numbers-Footnote-1344088 +Node: Locale influences conversions344197 +Ref: table-locale-affects346955 +Node: All Operators347573 +Node: Arithmetic Ops348202 +Node: Concatenation350708 +Ref: Concatenation-Footnote-1353555 +Node: Assignment Ops353662 +Ref: table-assign-ops358653 +Node: Increment Ops359966 +Node: Truth Values and Conditions363426 +Node: Truth Values364500 +Node: Typing and Comparison365548 +Node: Variable Typing366368 +Node: Comparison Operators369992 +Ref: table-relational-ops370411 +Node: POSIX String Comparison373906 +Ref: POSIX String Comparison-Footnote-1374980 +Node: Boolean Ops375119 +Ref: Boolean Ops-Footnote-1379601 +Node: Conditional Exp379693 +Node: Function Calls381429 +Node: Precedence385306 +Node: Locales388965 +Node: Expressions Summary390597 +Node: Patterns and Actions393170 +Node: Pattern Overview394290 +Node: Regexp Patterns395967 +Node: Expression Patterns396509 +Node: Ranges400290 +Node: BEGIN/END403398 +Node: Using BEGIN/END404159 +Ref: Using BEGIN/END-Footnote-1406895 +Node: I/O And BEGIN/END407001 +Node: BEGINFILE/ENDFILE409315 +Node: Empty412222 +Node: Using Shell Variables412539 +Node: Action Overview414813 +Node: Statements417138 +Node: If Statement418986 +Node: While Statement420481 +Node: Do Statement422509 +Node: For Statement423657 +Node: Switch Statement426815 +Node: Break Statement429201 +Node: Continue Statement431293 +Node: Next Statement433120 +Node: Nextfile Statement435503 +Node: Exit Statement438155 +Node: Built-in Variables440558 +Node: User-modified441691 +Node: Auto-set449277 +Ref: Auto-set-Footnote-1463664 +Ref: Auto-set-Footnote-2463870 +Node: ARGC and ARGV463926 +Node: Pattern Action Summary468139 +Node: Arrays470569 +Node: Array Basics471898 +Node: Array Intro472742 +Ref: figure-array-elements474717 +Ref: Array Intro-Footnote-1477421 +Node: Reference to Elements477549 +Node: Assigning Elements480013 +Node: Array Example480504 +Node: Scanning an Array482263 +Node: Controlling Scanning485285 +Ref: Controlling Scanning-Footnote-1490684 +Node: Numeric Array Subscripts491000 +Node: Uninitialized Subscripts493184 +Node: Delete494803 +Ref: Delete-Footnote-1497555 +Node: Multidimensional497612 +Node: Multiscanning500707 +Node: Arrays of Arrays502298 +Node: Arrays Summary507065 +Node: Functions509158 +Node: Built-in510196 +Node: Calling Built-in511274 +Node: Numeric Functions513270 +Ref: Numeric Functions-Footnote-1518103 +Ref: Numeric Functions-Footnote-2518460 +Ref: Numeric Functions-Footnote-3518508 +Node: String Functions518780 +Ref: String Functions-Footnote-1542284 +Ref: String Functions-Footnote-2542412 +Ref: String Functions-Footnote-3542660 +Node: Gory Details542747 +Ref: table-sub-escapes544538 +Ref: table-sub-proposed546057 +Ref: table-posix-sub547420 +Ref: table-gensub-escapes548961 +Ref: Gory Details-Footnote-1549784 +Node: I/O Functions549935 +Ref: I/O Functions-Footnote-1557155 +Node: Time Functions557303 +Ref: Time Functions-Footnote-1567808 +Ref: Time Functions-Footnote-2567876 +Ref: Time Functions-Footnote-3568034 +Ref: Time Functions-Footnote-4568145 +Ref: Time Functions-Footnote-5568257 +Ref: Time Functions-Footnote-6568484 +Node: Bitwise Functions568750 +Ref: table-bitwise-ops569344 +Ref: Bitwise Functions-Footnote-1573682 +Node: Type Functions573855 +Node: I18N Functions576516 +Node: User-defined578167 +Node: Definition Syntax578972 +Ref: Definition Syntax-Footnote-1584659 +Node: Function Example584730 +Ref: Function Example-Footnote-1587652 +Node: Function Caveats587674 +Node: Calling A Function588192 +Node: Variable Scope589150 +Node: Pass By Value/Reference592144 +Node: Return Statement595643 +Node: Dynamic Typing598622 +Node: Indirect Calls599552 +Ref: Indirect Calls-Footnote-1609803 +Node: Functions Summary609931 +Node: Library Functions612636 +Ref: Library Functions-Footnote-1616243 +Ref: Library Functions-Footnote-2616386 +Node: Library Names616557 +Ref: Library Names-Footnote-1620017 +Ref: Library Names-Footnote-2620240 +Node: General Functions620326 +Node: Strtonum Function621429 +Node: Assert Function624451 +Node: Round Function627777 +Node: Cliff Random Function629318 +Node: Ordinal Functions630334 +Ref: Ordinal Functions-Footnote-1633397 +Ref: Ordinal Functions-Footnote-2633649 +Node: Join Function633859 +Ref: Join Function-Footnote-1635629 +Node: Getlocaltime Function635829 +Node: Readfile Function639571 +Node: Shell Quoting641543 +Node: Data File Management642944 +Node: Filetrans Function643576 +Node: Rewind Function647672 +Node: File Checking649577 +Ref: File Checking-Footnote-1650911 +Node: Empty Files651112 +Node: Ignoring Assigns653091 +Node: Getopt Function654641 +Ref: Getopt Function-Footnote-1666110 +Node: Passwd Functions666310 +Ref: Passwd Functions-Footnote-1675149 +Node: Group Functions675237 +Ref: Group Functions-Footnote-1683134 +Node: Walking Arrays683341 +Node: Library Functions Summary686349 +Node: Library Exercises687755 +Node: Sample Programs688220 +Node: Running Examples688990 +Node: Clones689718 +Node: Cut Program690942 +Node: Egrep Program700871 +Ref: Egrep Program-Footnote-1708383 +Node: Id Program708493 +Node: Split Program712173 +Ref: Split Program-Footnote-1715632 +Node: Tee Program715761 +Node: Uniq Program718551 +Node: Wc Program725977 +Ref: Wc Program-Footnote-1730232 +Node: Miscellaneous Programs730326 +Node: Dupword Program731539 +Node: Alarm Program733569 +Node: Translate Program738424 +Ref: Translate Program-Footnote-1742989 +Node: Labels Program743259 +Ref: Labels Program-Footnote-1746610 +Node: Word Sorting746694 +Node: History Sorting750766 +Node: Extract Program752601 +Node: Simple Sed760130 +Node: Igawk Program763204 +Ref: Igawk Program-Footnote-1777535 +Ref: Igawk Program-Footnote-2777737 +Ref: Igawk Program-Footnote-3777859 +Node: Anagram Program777974 +Node: Signature Program781036 +Node: Programs Summary782283 +Node: Programs Exercises783497 +Ref: Programs Exercises-Footnote-1787626 +Node: Advanced Features787717 +Node: Nondecimal Data789707 +Node: Array Sorting791298 +Node: Controlling Array Traversal791998 +Ref: Controlling Array Traversal-Footnote-1800365 +Node: Array Sorting Functions800483 +Ref: Array Sorting Functions-Footnote-1805574 +Node: Two-way I/O805770 +Ref: Two-way I/O-Footnote-1811590 +Ref: Two-way I/O-Footnote-2811777 +Node: TCP/IP Networking811859 +Node: Profiling814977 +Node: Advanced Features Summary823431 +Node: Internationalization825275 +Node: I18N and L10N826755 +Node: Explaining gettext827442 +Ref: Explaining gettext-Footnote-1832465 +Ref: Explaining gettext-Footnote-2832650 +Node: Programmer i18n832815 +Ref: Programmer i18n-Footnote-1837670 +Node: Translator i18n837719 +Node: String Extraction838513 +Ref: String Extraction-Footnote-1839645 +Node: Printf Ordering839731 +Ref: Printf Ordering-Footnote-1842517 +Node: I18N Portability842581 +Ref: I18N Portability-Footnote-1845037 +Node: I18N Example845100 +Ref: I18N Example-Footnote-1847906 +Node: Gawk I18N847979 +Node: I18N Summary848624 +Node: Debugger849965 +Node: Debugging850987 +Node: Debugging Concepts851428 +Node: Debugging Terms853237 +Node: Awk Debugging855812 +Node: Sample Debugging Session856718 +Node: Debugger Invocation857252 +Node: Finding The Bug858638 +Node: List of Debugger Commands865116 +Node: Breakpoint Control866449 +Node: Debugger Execution Control870143 +Node: Viewing And Changing Data873505 +Node: Execution Stack876879 +Node: Debugger Info878516 +Node: Miscellaneous Debugger Commands882587 +Node: Readline Support887675 +Node: Limitations888571 +Ref: Limitations-Footnote-1892802 +Node: Debugging Summary892853 +Node: Arbitrary Precision Arithmetic894132 +Node: Computer Arithmetic895548 +Ref: table-numeric-ranges899139 +Ref: Computer Arithmetic-Footnote-1899861 +Node: Math Definitions899918 +Ref: table-ieee-formats903232 +Ref: Math Definitions-Footnote-1903835 +Node: MPFR features903940 +Node: FP Math Caution905657 +Ref: FP Math Caution-Footnote-1906729 +Node: Inexactness of computations907098 +Node: Inexact representation908058 +Node: Comparing FP Values909418 +Node: Errors accumulate910500 +Node: Getting Accuracy911933 +Node: Try To Round914643 +Node: Setting precision915542 +Ref: table-predefined-precision-strings916239 +Node: Setting the rounding mode918069 +Ref: table-gawk-rounding-modes918443 +Ref: Setting the rounding mode-Footnote-1921851 +Node: Arbitrary Precision Integers922030 +Ref: Arbitrary Precision Integers-Footnote-1926947 +Node: POSIX Floating Point Problems927096 +Ref: POSIX Floating Point Problems-Footnote-1930978 +Node: Floating point summary931016 +Node: Dynamic Extensions933206 +Node: Extension Intro934759 +Node: Plugin License936025 +Node: Extension Mechanism Outline936822 +Ref: figure-load-extension937261 +Ref: figure-register-new-function938826 +Ref: figure-call-new-function939918 +Node: Extension API Description941980 +Node: Extension API Functions Introduction943512 +Node: General Data Types948371 +Ref: General Data Types-Footnote-1954326 +Node: Memory Allocation Functions954625 +Ref: Memory Allocation Functions-Footnote-1957470 +Node: Constructor Functions957569 +Node: Registration Functions959314 +Node: Extension Functions959999 +Node: Exit Callback Functions962298 +Node: Extension Version String963548 +Node: Input Parsers964211 +Node: Output Wrappers974096 +Node: Two-way processors978608 +Node: Printing Messages980872 +Ref: Printing Messages-Footnote-1981946 +Node: Updating ERRNO982099 +Node: Requesting Values982838 +Ref: table-value-types-returned983575 +Node: Accessing Parameters984458 +Node: Symbol Table Access985693 +Node: Symbol table by name986205 +Node: Symbol table by cookie988226 +Ref: Symbol table by cookie-Footnote-1992375 +Node: Cached values992439 +Ref: Cached values-Footnote-1995940 +Node: Array Manipulation996031 +Ref: Array Manipulation-Footnote-1997122 +Node: Array Data Types997159 +Ref: Array Data Types-Footnote-1999817 +Node: Array Functions999909 +Node: Flattening Arrays1003767 +Node: Creating Arrays1010675 +Node: Redirection API1015446 +Node: Extension API Variables1018277 +Node: Extension Versioning1018910 +Node: Extension API Informational Variables1020801 +Node: Extension API Boilerplate1021865 +Node: Finding Extensions1025679 +Node: Extension Example1026238 +Node: Internal File Description1027036 +Node: Internal File Ops1031116 +Ref: Internal File Ops-Footnote-11042878 +Node: Using Internal File Ops1043018 +Ref: Using Internal File Ops-Footnote-11045401 +Node: Extension Samples1045675 +Node: Extension Sample File Functions1047204 +Node: Extension Sample Fnmatch1054853 +Node: Extension Sample Fork1056340 +Node: Extension Sample Inplace1057558 +Node: Extension Sample Ord1060768 +Node: Extension Sample Readdir1061604 +Ref: table-readdir-file-types1062493 +Node: Extension Sample Revout1063298 +Node: Extension Sample Rev2way1063887 +Node: Extension Sample Read write array1064627 +Node: Extension Sample Readfile1066569 +Node: Extension Sample Time1067664 +Node: Extension Sample API Tests1069012 +Node: gawkextlib1069504 +Node: Extension summary1071951 +Node: Extension Exercises1075643 +Node: Language History1077140 +Node: V7/SVR3.11078796 +Node: SVR41080948 +Node: POSIX1082382 +Node: BTL1083761 +Node: POSIX/GNU1084490 +Node: Feature History1090352 +Node: Common Extensions1104722 +Node: Ranges and Locales1106005 +Ref: Ranges and Locales-Footnote-11110621 +Ref: Ranges and Locales-Footnote-21110648 +Ref: Ranges and Locales-Footnote-31110883 +Node: Contributors1111104 +Node: History summary1116673 +Node: Installation1118053 +Node: Gawk Distribution1118997 +Node: Getting1119481 +Node: Extracting1120442 +Node: Distribution contents1122080 +Node: Unix Installation1128174 +Node: Quick Installation1128856 +Node: Shell Startup Files1131270 +Node: Additional Configuration Options1132348 +Node: Configuration Philosophy1134153 +Node: Non-Unix Installation1136522 +Node: PC Installation1136980 +Node: PC Binary Installation1138300 +Node: PC Compiling1140152 +Ref: PC Compiling-Footnote-11143176 +Node: PC Testing1143285 +Node: PC Using1144465 +Node: Cygwin1148579 +Node: MSYS1149349 +Node: VMS Installation1149850 +Node: VMS Compilation1150641 +Ref: VMS Compilation-Footnote-11151870 +Node: VMS Dynamic Extensions1151928 +Node: VMS Installation Details1153613 +Node: VMS Running1155866 +Node: VMS GNV1160145 +Node: VMS Old Gawk1160880 +Node: Bugs1161351 +Node: Other Versions1165548 +Node: Installation summary1172132 +Node: Notes1173190 +Node: Compatibility Mode1174055 +Node: Additions1174837 +Node: Accessing The Source1175762 +Node: Adding Code1177197 +Node: New Ports1183416 +Node: Derived Files1187904 +Ref: Derived Files-Footnote-11193389 +Ref: Derived Files-Footnote-21193424 +Ref: Derived Files-Footnote-31194022 +Node: Future Extensions1194136 +Node: Implementation Limitations1194794 +Node: Extension Design1195977 +Node: Old Extension Problems1197131 +Ref: Old Extension Problems-Footnote-11198649 +Node: Extension New Mechanism Goals1198706 +Ref: Extension New Mechanism Goals-Footnote-11202070 +Node: Extension Other Design Decisions1202259 +Node: Extension Future Growth1204372 +Node: Old Extension Mechanism1205208 +Node: Notes summary1206971 +Node: Basic Concepts1208153 +Node: Basic High Level1208834 +Ref: figure-general-flow1209116 +Ref: figure-process-flow1209801 +Ref: Basic High Level-Footnote-11213102 +Node: Basic Data Typing1213287 +Node: Glossary1216615 +Node: Copying1248561 +Node: GNU Free Documentation License1286100 +Node: Index1311218 End Tag Table diff --git a/doc/gawk.texi b/doc/gawk.texi index 33a823bc..002953eb 100644 --- a/doc/gawk.texi +++ b/doc/gawk.texi @@ -5662,6 +5662,15 @@ set. For example, @samp{[0-9]} is equivalent to @samp{[0123456789]}. standard and @command{gawk} have changed over time. This is mainly of historical interest.) +With the increasing popularity of the +@uref{http://www.unicode.org, Unicode character standard}, +there is an additional wrinkle to consider. Octal and hexadecimal +escape sequences inside bracket expressions are taken to represent +only single-byte characters (characters whose values fit within +the range 0--256). To match a range of characters where the endpoints +of the range are larger than 256, enter the multibyte encodings of +the characters directly. + @cindex @code{\} (backslash), in bracket expressions @cindex backslash (@code{\}), in bracket expressions @cindex @code{^} (caret), in bracket expressions diff --git a/doc/gawktexi.in b/doc/gawktexi.in index 7c9d473e..37bffc32 100644 --- a/doc/gawktexi.in +++ b/doc/gawktexi.in @@ -5490,6 +5490,15 @@ set. For example, @samp{[0-9]} is equivalent to @samp{[0123456789]}. standard and @command{gawk} have changed over time. This is mainly of historical interest.) +With the increasing popularity of the +@uref{http://www.unicode.org, Unicode character standard}, +there is an additional wrinkle to consider. Octal and hexadecimal +escape sequences inside bracket expressions are taken to represent +only single-byte characters (characters whose values fit within +the range 0--256). To match a range of characters where the endpoints +of the range are larger than 256, enter the multibyte encodings of +the characters directly. + @cindex @code{\} (backslash), in bracket expressions @cindex backslash (@code{\}), in bracket expressions @cindex @code{^} (caret), in bracket expressions @@ -1,5 +1,5 @@ /* Extended regular expression matching and search library. - Copyright (C) 2002-2015 Free Software Foundation, Inc. + Copyright (C) 2002-2016 Free Software Foundation, Inc. This file is part of the GNU C Library. Contributed by Isamu Hasegawa <isamu@yamato.ibm.com>. @@ -240,10 +240,8 @@ btowc (int c) are set in BUFP on entry. */ const char * -re_compile_pattern (pattern, length, bufp) - const char *pattern; - size_t length; - struct re_pattern_buffer *bufp; +re_compile_pattern (const char *pattern, size_t length, + struct re_pattern_buffer *bufp) { reg_errcode_t ret; @@ -281,8 +279,7 @@ reg_syntax_t re_syntax_options; defined in regex.h. We return the old syntax. */ reg_syntax_t -re_set_syntax (syntax) - reg_syntax_t syntax; +re_set_syntax (reg_syntax_t syntax) { reg_syntax_t ret = re_syntax_options; @@ -294,8 +291,7 @@ weak_alias (__re_set_syntax, re_set_syntax) #endif int -re_compile_fastmap (bufp) - struct re_pattern_buffer *bufp; +re_compile_fastmap (struct re_pattern_buffer *bufp) { re_dfa_t *dfa = (re_dfa_t *) bufp->buffer; char *fastmap = bufp->fastmap; @@ -494,10 +490,7 @@ re_compile_fastmap_iter (regex_t *bufp, const re_dfastate_t *init_state, the return codes and their meanings.) */ int -regcomp (preg, pattern, cflags) - regex_t *__restrict preg; - const char *__restrict pattern; - int cflags; +regcomp (regex_t *__restrict preg, const char *__restrict pattern, int cflags) { reg_errcode_t ret; reg_syntax_t syntax = ((cflags & REG_EXTENDED) ? RE_SYNTAX_POSIX_EXTENDED @@ -556,11 +549,8 @@ weak_alias (__regcomp, regcomp) from either regcomp or regexec. We don't use PREG here. */ size_t -regerror (errcode, preg, errbuf, errbuf_size) - int errcode; - const regex_t *__restrict preg; - char *__restrict errbuf; - size_t errbuf_size; +regerror (int errcode, const regex_t *__restrict preg, char *__restrict errbuf, + size_t errbuf_size) { const char *msg; size_t msg_size; @@ -667,8 +657,7 @@ free_dfa_content (re_dfa_t *dfa) /* Free dynamically allocated space used by PREG. */ void -regfree (preg) - regex_t *preg; +regfree (regex_t *preg) { re_dfa_t *dfa = (re_dfa_t *) preg->buffer; if (BE (dfa != NULL, 1)) @@ -701,8 +690,7 @@ char * regcomp/regexec above without link errors. */ weak_function # endif -re_comp (s) - const char *s; +re_comp (const char *s) { reg_errcode_t ret; char *fastmap; @@ -1,5 +1,5 @@ /* Extended regular expression matching and search library. - Copyright (C) 2002-2015 Free Software Foundation, Inc. + Copyright (C) 2002-2016 Free Software Foundation, Inc. This file is part of the GNU C Library. Contributed by Isamu Hasegawa <isamu@yamato.ibm.com>. @@ -1,6 +1,6 @@ /* Definitions for data structures and routines for the regular expression library. - Copyright (C) 1985, 1989-2015 Free Software Foundation, Inc. + Copyright (C) 1985, 1989-2016 Free Software Foundation, Inc. This file is part of the GNU C Library. The GNU C Library is free software; you can redistribute it and/or diff --git a/regex_internal.c b/regex_internal.c index 2d170932..759c7c81 100644 --- a/regex_internal.c +++ b/regex_internal.c @@ -320,12 +320,13 @@ build_wcs_upper_buffer (re_string_t *pstr) + byte_idx), remain_len, &pstr->cur_state); if (BE (mbclen + 2 > 2, 1)) { - wchar_t wcu = towupper (wc); - if (wcu != wc) + wchar_t wcu = wc; + if (iswlower (wc)) { size_t mbcdlen; - mbcdlen = wcrtomb (buf, wcu, &prev_st); + wcu = towupper (wc); + mbcdlen = __wcrtomb (buf, wcu, &prev_st); if (BE (mbclen == mbcdlen, 1)) memcpy (pstr->mbs + byte_idx, buf, mbclen); else @@ -389,11 +390,12 @@ build_wcs_upper_buffer (re_string_t *pstr) mbclen = __mbrtowc (&wc, p, remain_len, &pstr->cur_state); if (BE (mbclen + 2 > 2, 1)) { - wchar_t wcu = towupper (wc); - if (wcu != wc) + wchar_t wcu = wc; + if (iswlower (wc)) { size_t mbcdlen; + wcu = towupper (wc); mbcdlen = wcrtomb ((char *) buf, wcu, &prev_st); if (BE (mbclen == mbcdlen, 1)) memcpy (pstr->mbs + byte_idx, buf, mbclen); @@ -838,7 +840,7 @@ re_string_reconstruct (re_string_t *pstr, int idx, int eflags) } static unsigned char -internal_function __attribute__ ((pure)) +internal_function __attribute ((pure)) re_string_peek_byte_case (const re_string_t *pstr, int idx) { int ch, off; @@ -1370,7 +1372,7 @@ re_node_set_insert_last (re_node_set *set, int elem) return 1 if SET1 and SET2 are equivalent, return 0 otherwise. */ static int -internal_function __attribute__ ((pure)) +internal_function __attribute ((pure)) re_node_set_compare (const re_node_set *set1, const re_node_set *set2) { int i; @@ -1385,7 +1387,7 @@ re_node_set_compare (const re_node_set *set1, const re_node_set *set2) /* Return (idx + 1) if SET contains the element ELEM, return 0 otherwise. */ static int -internal_function __attribute__ ((pure)) +internal_function __attribute ((pure)) re_node_set_contains (const re_node_set *set, int elem) { unsigned int idx, right, mid; diff --git a/regex_internal.h b/regex_internal.h index 28b4239e..09f17b25 100644 --- a/regex_internal.h +++ b/regex_internal.h @@ -1,5 +1,5 @@ /* Extended regular expression matching and search library. - Copyright (C) 2002-2015 Free Software Foundation, Inc. + Copyright (C) 2002-2016 Free Software Foundation, Inc. This file is part of the GNU C Library. Contributed by Isamu Hasegawa <isamu@yamato.ibm.com>. @@ -45,7 +45,7 @@ # include <stdint.h> #endif /* HAVE_STDINT_H || _LIBC */ #if defined _LIBC -# include <bits/libc-lock.h> +# include <libc-lock.h> #else # define __libc_lock_define(CLASS,NAME) # define __libc_lock_init(NAME) do { } while (0) @@ -770,7 +770,7 @@ bitset_mask (bitset_t dest, const bitset_t src) } #ifdef RE_ENABLE_I18N -/* Functions for re_string. */ +/* Inline functions for re_string. */ static int internal_function __attribute__ ((pure, unused)) re_string_char_size_at (const re_string_t *pstr, int idx) @@ -229,12 +229,8 @@ MIN(size_t a, size_t b) We return 0 if we find a match and REG_NOMATCH if not. */ int -regexec (preg, string, nmatch, pmatch, eflags) - const regex_t *__restrict preg; - const char *__restrict string; - size_t nmatch; - regmatch_t pmatch[]; - int eflags; +regexec (const regex_t *__restrict preg, const char *__restrict string, + size_t nmatch, regmatch_t pmatch[], int eflags) { reg_errcode_t err; int start, length; @@ -314,11 +310,8 @@ compat_symbol (libc, __compat_regexec, regexec, GLIBC_2_0); match was found and -2 indicates an internal error. */ int -re_match (bufp, string, length, start, regs) - struct re_pattern_buffer *bufp; - const char *string; - int length, start; - struct re_registers *regs; +re_match (struct re_pattern_buffer *bufp, const char *string, int length, + int start, struct re_registers *regs) { return re_search_stub (bufp, string, length, start, 0, length, regs, 1); } @@ -327,11 +320,8 @@ weak_alias (__re_match, re_match) #endif int -re_search (bufp, string, length, start, range, regs) - struct re_pattern_buffer *bufp; - const char *string; - int length, start, range; - struct re_registers *regs; +re_search (struct re_pattern_buffer *bufp, const char *string, int length, + int start, int range, struct re_registers *regs) { return re_search_stub (bufp, string, length, start, range, length, regs, 0); } @@ -340,11 +330,9 @@ weak_alias (__re_search, re_search) #endif int -re_match_2 (bufp, string1, length1, string2, length2, start, regs, stop) - struct re_pattern_buffer *bufp; - const char *string1, *string2; - int length1, length2, start, stop; - struct re_registers *regs; +re_match_2 (struct re_pattern_buffer *bufp, const char *string1, int length1, + const char *string2, int length2, int start, + struct re_registers *regs, int stop) { return re_search_2_stub (bufp, string1, length1, string2, length2, start, 0, regs, stop, 1); @@ -354,11 +342,9 @@ weak_alias (__re_match_2, re_match_2) #endif int -re_search_2 (bufp, string1, length1, string2, length2, start, range, regs, stop) - struct re_pattern_buffer *bufp; - const char *string1, *string2; - int length1, length2, start, range, stop; - struct re_registers *regs; +re_search_2 (struct re_pattern_buffer *bufp, const char *string1, int length1, + const char *string2, int length2, int start, int range, + struct re_registers *regs, int stop) { return re_search_2_stub (bufp, string1, length1, string2, length2, start, range, regs, stop, 0); @@ -368,12 +354,11 @@ weak_alias (__re_search_2, re_search_2) #endif static int -re_search_2_stub (bufp, string1, length1, string2, length2, start, range, regs, - stop, ret_len) - struct re_pattern_buffer *bufp; - const char *string1, *string2; - int length1, length2, start, range, stop, ret_len; - struct re_registers *regs; +internal_function +re_search_2_stub (struct re_pattern_buffer *bufp, const char *string1, + int length1, const char *string2, int length2, int start, + int range, struct re_registers *regs, + int stop, int ret_len) { const char *str; int rval; @@ -415,11 +400,10 @@ re_search_2_stub (bufp, string1, length1, string2, length2, start, range, regs, otherwise the position of the match is returned. */ static int -re_search_stub (bufp, string, length, start, range, stop, regs, ret_len) - struct re_pattern_buffer *bufp; - const char *string; - int length, start, range, stop, ret_len; - struct re_registers *regs; +internal_function +re_search_stub (struct re_pattern_buffer *bufp, const char *string, int length, + int start, int range, int stop, struct re_registers *regs, + int ret_len) { reg_errcode_t result; regmatch_t *pmatch; @@ -503,10 +487,9 @@ re_search_stub (bufp, string, length, start, range, stop, regs, ret_len) } static unsigned -re_copy_regs (regs, pmatch, nregs, regs_allocated) - struct re_registers *regs; - regmatch_t *pmatch; - int nregs, regs_allocated; +internal_function +re_copy_regs (struct re_registers *regs, regmatch_t *pmatch, int nregs, + int regs_allocated) { int rval = REGS_REALLOCATE; int i; @@ -583,11 +566,8 @@ re_copy_regs (regs, pmatch, nregs, regs_allocated) freeing the old data. */ void -re_set_registers (bufp, regs, num_regs, starts, ends) - struct re_pattern_buffer *bufp; - struct re_registers *regs; - unsigned num_regs; - regoff_t *starts, *ends; +re_set_registers (struct re_pattern_buffer *bufp, struct re_registers *regs, + unsigned num_regs, regoff_t *starts, regoff_t *ends) { if (num_regs) { @@ -615,8 +595,7 @@ int # ifdef _LIBC weak_function # endif -re_exec (s) - const char *s; +re_exec (const char *s) { return 0 == regexec (&re_comp_buf, s, 0, NULL, 0); } @@ -634,14 +613,10 @@ re_exec (s) (START + RANGE >= 0 && START + RANGE <= LENGTH) */ static reg_errcode_t -__attribute_warn_unused_result__ -re_search_internal (preg, string, length, start, range, stop, nmatch, pmatch, - eflags) - const regex_t *preg; - const char *string; - int length, start, range, stop, eflags; - size_t nmatch; - regmatch_t pmatch[]; +__attribute_warn_unused_result__ internal_function +re_search_internal (const regex_t *preg, const char *string, int length, + int start, int range, int stop, size_t nmatch, + regmatch_t pmatch[], int eflags) { reg_errcode_t err; const re_dfa_t *dfa = (const re_dfa_t *) preg->buffer; @@ -962,6 +937,7 @@ re_search_internal (preg, string, length, start, range, stop, nmatch, pmatch, } static reg_errcode_t +internal_function __attribute_warn_unused_result__ prune_impossible_nodes (re_match_context_t *mctx) { const re_dfa_t *const dfa = mctx->dfa; @@ -1057,7 +1033,7 @@ prune_impossible_nodes (re_match_context_t *mctx) since initial states may have constraints like "\<", "^", etc.. */ static inline re_dfastate_t * -__attribute__ ((always_inline)) internal_function +__attribute ((always_inline)) internal_function acquire_init_state_context (reg_errcode_t *err, const re_match_context_t *mctx, int idx) { |