diff options
| -rw-r--r-- | ChangeLog | 10 | ||||
| -rw-r--r-- | custom.h | 14 | ||||
| -rw-r--r-- | dfa.c | 420 | ||||
| -rw-r--r-- | dfa.h | 18 | ||||
| -rw-r--r-- | doc/ChangeLog | 4 | ||||
| -rw-r--r-- | doc/gawk.info | 1032 | ||||
| -rw-r--r-- | doc/gawk.texi | 17 | ||||
| -rw-r--r-- | doc/gawktexi.in | 17 |
8 files changed, 808 insertions, 724 deletions
@@ -1,3 +1,13 @@ +2014-05-14 Arnold D. Robbins <arnold@skeeve.com> + + * custom.h (_GL_PURE): Move definition to here. Sigh. + * dfa.h, dfa.c: Sync with GNU grep. Sigh. + + Unrelated: + + * custom.h: Remove stuff for Ultrix 4.3. No one has such + systems anymore; this just got missed earlier. + 2014-05-11 Arnold D. Robbins <arnold@skeeve.com> * debug.c (do_eval): Repair fix of 2014-05-09 and use @@ -47,12 +47,6 @@ #define HAVE_MKTIME 1 #endif -/* For ULTRIX 4.3 */ -#ifdef ultrix -#define HAVE_MKTIME 1 -#define GETGROUPS_NOT_STANDARD 1 -#endif - /* For whiny users */ #ifdef USE_INCLUDED_STRFTIME #undef HAVE_STRFTIME @@ -76,3 +70,11 @@ extern int setenv(const char *name, const char *value, int rewrite); extern int unsetenv(const char *name); #endif + +/* Junk for dfa.[ch] */ +/* The __pure__ attribute was added in gcc 2.96. */ +#if __GNUC__ > 2 || (__GNUC__ == 2 && __GNUC_MINOR__ >= 96) +# define _GL_ATTRIBUTE_PURE __attribute__ ((__pure__)) +#else +# define _GL_ATTRIBUTE_PURE /* empty */ +#endif @@ -55,7 +55,6 @@ host does not conform to Posix. */ #define ISASCIIDIGIT(c) ((unsigned) (c) - '0' <= 9) -/* gettext.h ensures that we don't use gettext if ENABLE_NLS is not defined */ #include "gettext.h" #define _(str) gettext (str) @@ -66,15 +65,6 @@ # include <wctype.h> #endif -#ifdef GAWK -/* The __pure__ attribute was added in gcc 2.96. */ -#if __GNUC__ > 2 || (__GNUC__ == 2 && __GNUC_MINOR__ >= 96) -# define _GL_ATTRIBUTE_PURE __attribute__ ((__pure__)) -#else -# define _GL_ATTRIBUTE_PURE /* empty */ -#endif -#endif /* GAWK */ - #include "xalloc.h" #include "dfa.h" @@ -103,24 +93,29 @@ extern int gawk_mb_cur_max; # undef clrbit #endif -/* Number of bits in an unsigned char. */ -#ifndef CHARBITS -# define CHARBITS 8 -#endif - /* First integer value that is greater than any character code. */ -#define NOTCHAR (1 << CHARBITS) +enum { NOTCHAR = 1 << CHAR_BIT }; -/* INTBITS need not be exact, just a lower bound. */ -#ifndef INTBITS -# define INTBITS (CHARBITS * sizeof (int)) -#endif +/* This represents part of a character class. It must be unsigned and + at least CHARCLASS_WORD_BITS wide. Any excess bits are zero. */ +typedef unsigned int charclass_word; + +/* The number of bits used in a charclass word. utf8_classes assumes + this is exactly 32. */ +enum { CHARCLASS_WORD_BITS = 32 }; -/* Number of ints required to hold a bit for every character. */ -#define CHARCLASS_INTS ((NOTCHAR + INTBITS - 1) / INTBITS) +/* The maximum useful value of a charclass_word; all used bits are 1. */ +#define CHARCLASS_WORD_MASK \ + (((charclass_word) 1 << (CHARCLASS_WORD_BITS - 1) << 1) - 1) + +/* Number of words required to hold a bit for every character. */ +enum +{ + CHARCLASS_WORDS = (NOTCHAR + CHARCLASS_WORD_BITS - 1) / CHARCLASS_WORD_BITS +}; /* Sets of unsigned characters are stored as bit vectors in arrays of ints. */ -typedef unsigned int charclass[CHARCLASS_INTS]; +typedef charclass_word charclass[CHARCLASS_WORDS]; /* Convert a possibly-signed character to an unsigned character. This is a bit safer than casting to unsigned char, since it catches some type @@ -223,27 +218,25 @@ enum a backtracking matcher. */ BEGLINE, /* BEGLINE is a terminal symbol that matches - the empty string if it is at the beginning - of a line. */ + the empty string at the beginning of a + line. */ ENDLINE, /* ENDLINE is a terminal symbol that matches - the empty string if it is at the end of - a line. */ + the empty string at the end of a line. */ BEGWORD, /* BEGWORD is a terminal symbol that matches - the empty string if it is at the beginning - of a word. */ + the empty string at the beginning of a + word. */ ENDWORD, /* ENDWORD is a terminal symbol that matches - the empty string if it is at the end of - a word. */ + the empty string at the end of a word. */ LIMWORD, /* LIMWORD is a terminal symbol that matches - the empty string if it is at the beginning - or the end of a word. */ + the empty string at the beginning or the + end of a word. */ NOTLIMWORD, /* NOTLIMWORD is a terminal symbol that - matches the empty string if it is not at + matches the empty string not at the beginning or end of a word. */ QMARK, /* QMARK is an operator of one argument that @@ -324,8 +317,8 @@ typedef struct size_t hash; /* Hash of the positions of this state. */ position_set elems; /* Positions this state could match. */ unsigned char context; /* Context from previous state. */ - bool has_backref; /* True if this state matches a \<digit>. */ - bool has_mbcset; /* True if this state matches a MBCSET. */ + bool has_backref; /* This state matches a \<digit>. */ + bool has_mbcset; /* This state matches a MBCSET. */ unsigned short constraint; /* Constraint for this state to accept. */ token first_end; /* Token value of the first END in elems. */ position_set mbps; /* Positions which can match multibyte @@ -377,7 +370,8 @@ struct dfa size_t nleaves; /* Number of leaves on the parse tree. */ size_t nregexps; /* Count of parallel regexps being built with dfaparse. */ - bool multibyte; /* True iff MB_CUR_MAX > 1. */ + bool fast; /* The DFA is fast. */ + bool multibyte; /* MB_CUR_MAX > 1. */ token utf8_anychar_classes[5]; /* To lower ANYCHAR in UTF-8 locales. */ mbstate_t mbs; /* Multibyte conversion state. */ @@ -404,9 +398,8 @@ struct dfa #if MBS_SUPPORT /* A table indexed by byte values that contains the corresponding wide - character (if any) for that byte. WEOF means the byte is the - leading byte of a multibyte character. Invalid and null bytes are - mapped to themselves. */ + character (if any) for that byte. WEOF means the byte is not a + valid single-byte character. */ wint_t mbrtowc_cache[NOTCHAR]; #endif @@ -431,7 +424,7 @@ struct dfa matching the given position in a string matching the regexp. Allocated to the maximum possible position index. */ - bool searchflag; /* True if we are supposed to build a searching + bool searchflag; /* We are supposed to build a searching as opposed to an exact matcher. A searching matcher finds the first and shortest string matching a regexp anywhere in the buffer, @@ -474,11 +467,10 @@ struct dfa /* Some macros for user access to dfa internals. */ -/* ACCEPTING returns true if s could possibly be an accepting state of r. */ +/* S could possibly be an accepting state of R. */ #define ACCEPTING(s, r) ((r).states[s].constraint) -/* ACCEPTS_IN_CONTEXT returns true if the given state accepts in the - specified context. */ +/* STATE accepts in the specified context. */ #define ACCEPTS_IN_CONTEXT(prev, curr, state, dfa) \ SUCCEEDS_IN_CONTEXT ((dfa).states[state].constraint, prev, curr) @@ -496,14 +488,7 @@ dfambcache (struct dfa *d) unsigned char uc = i; mbstate_t s = { 0 }; wchar_t wc; - wint_t wi; - switch (mbrtowc (&wc, &c, 1, &s)) - { - default: wi = wc; break; - case (size_t) -2: wi = WEOF; break; - case (size_t) -1: wi = uc; break; - } - d->mbrtowc_cache[uc] = wi; + d->mbrtowc_cache[uc] = mbrtowc (&wc, &c, 1, &s) <= 1 ? wc : WEOF; } #endif } @@ -512,11 +497,12 @@ dfambcache (struct dfa *d) /* Store into *PWC the result of converting the leading bytes of the multibyte buffer S of length N bytes, using the mbrtowc_cache in *D and updating the conversion state in *D. On conversion error, - convert just a single byte as-is. Return the number of bytes + convert just a single byte, to WEOF. Return the number of bytes converted. This differs from mbrtowc (PWC, S, N, &D->mbs) as follows: + * PWC points to wint_t, not to wchar_t. * The last arg is a dfa *D instead of merely a multibyte conversion state D->mbs. D also contains an mbrtowc_cache for speed. * N must be at least 1. @@ -526,18 +512,21 @@ dfambcache (struct dfa *d) * D->mbs is always valid afterwards. * *PWC is always set to something. */ static size_t -mbs_to_wchar (wchar_t *pwc, char const *s, size_t n, struct dfa *d) +mbs_to_wchar (wint_t *pwc, char const *s, size_t n, struct dfa *d) { unsigned char uc = s[0]; wint_t wc = d->mbrtowc_cache[uc]; if (wc == WEOF) { - size_t nbytes = mbrtowc (pwc, s, n, &d->mbs); + wchar_t wch; + size_t nbytes = mbrtowc (&wch, s, n, &d->mbs); if (0 < nbytes && nbytes < (size_t) -2) - return nbytes; + { + *pwc = wch; + return nbytes; + } memset (&d->mbs, 0, sizeof d->mbs); - wc = uc; } *pwc = wc; @@ -628,19 +617,20 @@ prtok (token t) static bool tstbit (unsigned int b, charclass const c) { - return c[b / INTBITS] >> b % INTBITS & 1; + return c[b / CHARCLASS_WORD_BITS] >> b % CHARCLASS_WORD_BITS & 1; } static void setbit (unsigned int b, charclass c) { - c[b / INTBITS] |= 1U << b % INTBITS; + c[b / CHARCLASS_WORD_BITS] |= (charclass_word) 1 << b % CHARCLASS_WORD_BITS; } static void clrbit (unsigned int b, charclass c) { - c[b / INTBITS] &= ~(1U << b % INTBITS); + c[b / CHARCLASS_WORD_BITS] &= ~((charclass_word) 1 + << b % CHARCLASS_WORD_BITS); } static void @@ -660,8 +650,8 @@ notset (charclass s) { int i; - for (i = 0; i < CHARCLASS_INTS; ++i) - s[i] = ~s[i]; + for (i = 0; i < CHARCLASS_WORDS; ++i) + s[i] = CHARCLASS_WORD_MASK & ~s[i]; } static bool @@ -675,9 +665,9 @@ equal (charclass const s1, charclass const s2) and return its new address. Although PTR may be null, the returned value is never null. - The array holds *NALLOC items; *NALLOC must be zero if PTR is null, - and is updated on reallocation. ITEMSIZE is the size of one item. - Avoid O(N**2) behavior on arrays growing linearly. */ + The array holds *NALLOC items; *NALLOC is updated on reallocation. + ITEMSIZE is the size of one item. Avoid O(N**2) behavior on arrays + growing linearly. */ static void * maybe_realloc (void *ptr, size_t nitems, size_t *nalloc, size_t itemsize) { @@ -740,7 +730,7 @@ static charclass newline; # define is_valid_unibyte_character(c) (! (MBS_SUPPORT && btowc (c) == WEOF)) #endif -/* Return non-zero if C is a "word-constituent" byte; zero otherwise. */ +/* C is a "word-constituent" byte. */ #define IS_WORD_CONSTITUENT(C) \ (is_valid_unibyte_character (C) && (isalnum (C) || (C) == '_')) @@ -844,7 +834,7 @@ using_utf8 (void) return utf8; } -/* Return true if the current locale is known to be a unibyte locale +/* The current locale is known to be a unibyte locale without multicharacter collating sequences and where range comparisons simply use the native encoding. These locales can be processed more efficiently. */ @@ -852,7 +842,7 @@ using_utf8 (void) static bool using_simple_locale (void) { - /* True if the native character set is known to be compatible with + /* The native character set is known to be compatible with the C locale. The following test isn't perfect, but it's good enough in practice, as only ASCII and EBCDIC are in common use and this test correctly accepts ASCII and rejects EBCDIC. */ @@ -868,7 +858,7 @@ using_simple_locale (void) && '}' == 125 && '~' == 126) }; - if (! native_c_charset || MB_CUR_MAX > 1) + if (! native_c_charset || dfa->multibyte) return false; else { @@ -892,20 +882,28 @@ using_simple_locale (void) static char const *lexptr; /* Pointer to next input character. */ static size_t lexleft; /* Number of characters remaining. */ static token lasttok; /* Previous token returned; initially END. */ -static bool laststart; /* True if we're separated from beginning or (, +static bool laststart; /* We're separated from beginning or (, | only by zero-width characters. */ static size_t parens; /* Count of outstanding left parens. */ static int minrep, maxrep; /* Repeat counts for {m,n}. */ static int cur_mb_len = 1; /* Length of the multibyte representation of wctok. */ -/* These variables are used only if (MB_CUR_MAX > 1). */ -static wchar_t wctok; /* Wide character representation of the current - multibyte character. */ + +static wint_t wctok; /* Wide character representation of the current + multibyte character, or WEOF if there was + an encoding error. Used only if + MB_CUR_MAX > 1. */ #if MBS_SUPPORT -/* Note that characters become unsigned here. */ +/* Fetch the next lexical input character. Set C (of type int) to the + next input byte, except set C to EOF if the input is a multibyte + character of length greater than 1. Set WC (of type wint_t) to the + value of the input if it is a valid multibyte character (possibly + of length 1); otherwise set WC to WEOF. If there is no more input, + report EOFERR if EOFERR is not null, and return lasttok = END + otherwise. */ # define FETCH_WC(c, wc, eoferr) \ do { \ if (! lexleft) \ @@ -917,7 +915,7 @@ static wchar_t wctok; /* Wide character representation of the current } \ else \ { \ - wchar_t _wc; \ + wint_t _wc; \ size_t nbytes = mbs_to_wchar (&_wc, lexptr, lexleft, dfa); \ cur_mb_len = nbytes; \ (wc) = _wc; \ @@ -1044,7 +1042,7 @@ parse_bracket_exp (void) int c, c1, c2; charclass ccl; - /* True if this is a bracket expression that dfaexec is known to + /* This is a bracket expression that dfaexec is known to process correctly. */ bool known_bracket_exp = true; @@ -1095,7 +1093,7 @@ parse_bracket_exp (void) colon_warning_state = (c == ':'); do { - c1 = EOF; /* mark c1 is not initialized". */ + c1 = NOTCHAR; /* Mark c1 as not initialized. */ colon_warning_state &= ~2; /* Note that if we're looking at some other [:...:] construct, @@ -1104,13 +1102,13 @@ parse_bracket_exp (void) dfa is ever called. */ if (c == '[') { -#define MAX_BRACKET_STRING_LEN 32 - char str[MAX_BRACKET_STRING_LEN + 1]; FETCH_WC (c1, wc1, _("unbalanced [")); if ((c1 == ':' && (syntax_bits & RE_CHAR_CLASSES)) || c1 == '.' || c1 == '=') { + enum { MAX_BRACKET_STRING_LEN = 32 }; + char str[MAX_BRACKET_STRING_LEN + 1]; size_t len = 0; for (;;) { @@ -1173,7 +1171,7 @@ parse_bracket_exp (void) if (c == '\\' && (syntax_bits & RE_BACKSLASH_ESCAPE_IN_LISTS)) FETCH_WC (c, wc, _("unbalanced [")); - if (c1 == EOF) + if (c1 == NOTCHAR) FETCH_WC (c1, wc1, _("unbalanced [")); if (c1 == '-') @@ -1201,19 +1199,22 @@ parse_bracket_exp (void) to the pair of ranges, [m-z] [M-Z]. Although this code is wrong in multiple ways, it's never used in practice. FIXME: Remove this (and related) unused code. */ - work_mbc->ranges - = maybe_realloc (work_mbc->ranges, work_mbc->nranges + 2, - &ranges_al, sizeof *work_mbc->ranges); - work_mbc->ranges[work_mbc->nranges].beg - = case_fold ? towlower (wc) : wc; - work_mbc->ranges[work_mbc->nranges++].end - = case_fold ? towlower (wc2) : wc2; - - if (case_fold && (iswalpha (wc) || iswalpha (wc2))) + if (wc != WEOF && wc2 != WEOF) { - work_mbc->ranges[work_mbc->nranges].beg = towupper (wc); + work_mbc->ranges + = maybe_realloc (work_mbc->ranges, work_mbc->nranges + 2, + &ranges_al, sizeof *work_mbc->ranges); + work_mbc->ranges[work_mbc->nranges].beg + = case_fold ? towlower (wc) : wc; work_mbc->ranges[work_mbc->nranges++].end - = towupper (wc2); + = case_fold ? towlower (wc2) : wc2; + + if (case_fold && (iswalpha (wc) || iswalpha (wc2))) + { + work_mbc->ranges[work_mbc->nranges].beg = towupper (wc); + work_mbc->ranges[work_mbc->nranges++].end + = towupper (wc2); + } } } else if (using_simple_locale ()) @@ -1257,22 +1258,23 @@ parse_bracket_exp (void) continue; } - if (case_fold) + if (wc == WEOF) + known_bracket_exp = false; + else { - wchar_t folded[CASE_FOLDED_BUFSIZE]; - int i, n = case_folded_counterparts (wc, folded); - work_mbc->chars = maybe_realloc (work_mbc->chars, - work_mbc->nchars + n, &chars_al, - sizeof *work_mbc->chars); + wchar_t folded[CASE_FOLDED_BUFSIZE + 1]; + int i; + int n = (case_fold ? case_folded_counterparts (wc, folded + 1) + 1 + : 1); + folded[0] = wc; for (i = 0; i < n; i++) if (!setbit_wc (folded[i], ccl)) - work_mbc->chars[work_mbc->nchars++] = folded[i]; - } - if (!setbit_wc (wc, ccl)) - { - work_mbc->chars = maybe_realloc (work_mbc->chars, work_mbc->nchars, - &chars_al, sizeof *work_mbc->chars); - work_mbc->chars[work_mbc->nchars++] = wc; + { + work_mbc->chars + = maybe_realloc (work_mbc->chars, work_mbc->nchars, + &chars_al, sizeof *work_mbc->chars); + work_mbc->chars[work_mbc->nchars++] = folded[i]; + } } } while ((wc = wc1, (c = c1) != ']')); @@ -1305,7 +1307,7 @@ parse_bracket_exp (void) static token lex (void) { - unsigned int c, c2; + int c, c2; bool backslash = false; charclass ccl; int i; @@ -1319,8 +1321,6 @@ lex (void) for (i = 0; i < 2; ++i) { FETCH_WC (c, wctok, NULL); - if (c == (unsigned int) EOF) - goto normal_char; switch (c) { @@ -1660,8 +1660,12 @@ addtok_mb (token t, int mbprop) --depth; break; + case BACKREF: + dfa->fast = false; + /* fallthrough */ default: ++dfa->nleaves; + /* fallthrough */ case EMPTY: ++depth; break; @@ -1772,11 +1776,21 @@ add_utf8_anychar (void) { #if MBS_SUPPORT static const charclass utf8_classes[5] = { - {0, 0, 0, 0, ~0, ~0, 0, 0}, /* 80-bf: non-leading bytes */ - {~0, ~0, ~0, ~0, 0, 0, 0, 0}, /* 00-7f: 1-byte sequence */ - {0, 0, 0, 0, 0, 0, ~3, 0}, /* c2-df: 2-byte sequence */ - {0, 0, 0, 0, 0, 0, 0, 0xffff}, /* e0-ef: 3-byte sequence */ - {0, 0, 0, 0, 0, 0, 0, 0xff0000} /* f0-f7: 4-byte sequence */ + /* 80-bf: non-leading bytes. */ + {0, 0, 0, 0, CHARCLASS_WORD_MASK, CHARCLASS_WORD_MASK, 0, 0}, + + /* 00-7f: 1-byte sequence. */ + {CHARCLASS_WORD_MASK, CHARCLASS_WORD_MASK, CHARCLASS_WORD_MASK, + CHARCLASS_WORD_MASK, 0, 0, 0, 0}, + + /* c2-df: 2-byte sequence. */ + {0, 0, 0, 0, 0, 0, ~3 & CHARCLASS_WORD_MASK, 0}, + + /* e0-ef: 3-byte sequence. */ + {0, 0, 0, 0, 0, 0, 0, 0xffff}, + + /* f0-f7: 4-byte sequence. */ + {0, 0, 0, 0, 0, 0, 0, 0xff0000} }; const unsigned int n = sizeof (utf8_classes) / sizeof (utf8_classes[0]); unsigned int i; @@ -1858,16 +1872,21 @@ atom (void) { if (MBS_SUPPORT && tok == WCHAR) { - addtok_wc (wctok); - - if (case_fold) + if (wctok == WEOF) + addtok (BACKREF); + else { - wchar_t folded[CASE_FOLDED_BUFSIZE]; - int i, n = case_folded_counterparts (wctok, folded); - for (i = 0; i < n; i++) + addtok_wc (wctok); + + if (case_fold) { - addtok_wc (folded[i]); - addtok (OR); + wchar_t folded[CASE_FOLDED_BUFSIZE]; + int i, n = case_folded_counterparts (wctok, folded); + for (i = 0; i < n; i++) + { + addtok_wc (folded[i]); + addtok (OR); + } } } @@ -2213,13 +2232,11 @@ state_index (struct dfa *d, position_set const *s, int context) constraint. Repeat exhaustively until no funny positions are left. S->elems must be large enough to hold the result. */ static void -epsclosure (position_set * s, struct dfa const *d) +epsclosure (position_set *s, struct dfa const *d, char *visited) { size_t i, j; position p, old; - - /* Array of booleans, large enough to use char, not int. */ - char *visited = xzalloc (d->tindex); + bool initialized = false; for (i = 0; i < s->nelem; ++i) if (d->tokens[s->elems[i].index] >= NOTCHAR @@ -2230,6 +2247,11 @@ epsclosure (position_set * s, struct dfa const *d) #endif && d->tokens[s->elems[i].index] < CSET) { + if (!initialized) + { + memset (visited, 0, d->tindex * sizeof (*visited)); + initialized = true; + } old = s->elems[i]; p.constraint = old.constraint; delete (s->elems[i], s); @@ -2270,8 +2292,6 @@ epsclosure (position_set * s, struct dfa const *d) /* Force rescan to start at the beginning. */ i = -1; } - - free (visited); } /* Returns the set of contexts for which there is at least one @@ -2286,7 +2306,7 @@ charclass_context (charclass c) if (tstbit (eolbyte, c)) context |= CTX_NEWLINE; - for (j = 0; j < CHARCLASS_INTS; ++j) + for (j = 0; j < CHARCLASS_WORDS; ++j) { if (c[j] & letters[j]) context |= CTX_LETTER; @@ -2398,6 +2418,7 @@ dfaanalyze (struct dfa *d, int searchflag) int separate_contexts; /* Context wanted by some position. */ size_t i, j; position *pos; + char *visited = xnmalloc (d->tindex, sizeof *visited); #ifdef DEBUG fprintf (stderr, "dfaanalyze:\n"); @@ -2438,6 +2459,7 @@ dfaanalyze (struct dfa *d, int searchflag) merge (&tmp, &d->follows[pos[j].index], &merged); copy (&merged, &d->follows[pos[j].index]); } + /* fallthrough */ case QMARK: /* A QMARK or STAR node is automatically nullable. */ @@ -2558,7 +2580,7 @@ dfaanalyze (struct dfa *d, int searchflag) putc ('\n', stderr); #endif copy (&d->follows[i], &merged); - epsclosure (&merged, d); + epsclosure (&merged, d, visited); copy (&merged, &d->follows[i]); } @@ -2567,7 +2589,7 @@ dfaanalyze (struct dfa *d, int searchflag) merged.nelem = 0; for (i = 0; i < stk[-1].nfirstpos; ++i) insert (firstpos[i], &merged); - epsclosure (&merged, d); + epsclosure (&merged, d, visited); /* Build the initial state. */ separate_contexts = state_separate_contexts (&merged); @@ -2578,6 +2600,7 @@ dfaanalyze (struct dfa *d, int searchflag) free (posalloc); free (stkalloc); free (merged.elems); + free (visited); } @@ -2619,11 +2642,11 @@ dfastate (state_num s, struct dfa *d, state_num trans[]) size_t ngrps = 0; /* Number of groups actually used. */ position pos; /* Current position being considered. */ charclass matches; /* Set of matching characters. */ - unsigned int matchesf; /* Nonzero if matches is nonempty. */ + charclass_word matchesf; /* Nonzero if matches is nonempty. */ charclass intersect; /* Intersection with some label set. */ - unsigned int intersectf; /* Nonzero if intersect is nonempty. */ + charclass_word intersectf; /* Nonzero if intersect is nonempty. */ charclass leftovers; /* Stuff in the label that didn't match. */ - unsigned int leftoversf; /* Nonzero if leftovers is nonempty. */ + charclass_word leftoversf; /* Nonzero if leftovers is nonempty. */ position_set follows; /* Union of the follows of some group. */ position_set tmp; /* Temporary space for merging sets. */ int possible_contexts; /* Contexts that this group can match. */ @@ -2631,7 +2654,7 @@ dfastate (state_num s, struct dfa *d, state_num trans[]) state_num state; /* New state. */ state_num state_newline; /* New state on a newline transition. */ state_num state_letter; /* New state on a letter transition. */ - bool next_isnt_1st_byte = false; /* Flag if we can't add state0. */ + bool next_isnt_1st_byte = false; /* We can't add state0. */ size_t i, j, k; zeroset (matches); @@ -2643,21 +2666,24 @@ dfastate (state_num s, struct dfa *d, state_num trans[]) setbit (d->tokens[pos.index], matches); else if (d->tokens[pos.index] >= CSET) copyset (d->charclasses[d->tokens[pos.index] - CSET], matches); - else if (MBS_SUPPORT - && (d->tokens[pos.index] == ANYCHAR - || d->tokens[pos.index] == MBCSET)) - /* MB_CUR_MAX > 1 */ + else { - /* ANYCHAR and MBCSET must match with a single character, so we - must put it to d->states[s].mbps, which contains the positions - which can match with a single character not a byte. */ - if (d->states[s].mbps.nelem == 0) - alloc_position_set (&d->states[s].mbps, 1); - insert (pos, &(d->states[s].mbps)); + if (MBS_SUPPORT + && (d->tokens[pos.index] == MBCSET + || d->tokens[pos.index] == ANYCHAR)) + { + /* MB_CUR_MAX > 1 */ + if (d->tokens[pos.index] == MBCSET) + d->states[s].has_mbcset = true; + /* ANYCHAR and MBCSET must match with a single character, so we + must put it to d->states[s].mbps, which contains the positions + which can match with a single character not a byte. */ + if (d->states[s].mbps.nelem == 0) + alloc_position_set (&d->states[s].mbps, 1); + insert (pos, &(d->states[s].mbps)); + } continue; } - else - continue; /* Some characters may need to be eliminated from matches because they fail in the current context. */ @@ -2665,21 +2691,21 @@ dfastate (state_num s, struct dfa *d, state_num trans[]) { if (!SUCCEEDS_IN_CONTEXT (pos.constraint, d->states[s].context, CTX_NEWLINE)) - for (j = 0; j < CHARCLASS_INTS; ++j) + for (j = 0; j < CHARCLASS_WORDS; ++j) matches[j] &= ~newline[j]; if (!SUCCEEDS_IN_CONTEXT (pos.constraint, d->states[s].context, CTX_LETTER)) - for (j = 0; j < CHARCLASS_INTS; ++j) + for (j = 0; j < CHARCLASS_WORDS; ++j) matches[j] &= ~letters[j]; if (!SUCCEEDS_IN_CONTEXT (pos.constraint, d->states[s].context, CTX_NONE)) - for (j = 0; j < CHARCLASS_INTS; ++j) + for (j = 0; j < CHARCLASS_WORDS; ++j) matches[j] &= letters[j] | newline[j]; /* If there are no characters left, there's no point in going on. */ - for (j = 0; j < CHARCLASS_INTS && !matches[j]; ++j) + for (j = 0; j < CHARCLASS_WORDS && !matches[j]; ++j) continue; - if (j == CHARCLASS_INTS) + if (j == CHARCLASS_WORDS) continue; } @@ -2695,17 +2721,17 @@ dfastate (state_num s, struct dfa *d, state_num trans[]) /* Check if this group's label has a nonempty intersection with matches. */ intersectf = 0; - for (k = 0; k < CHARCLASS_INTS; ++k) + for (k = 0; k < CHARCLASS_WORDS; ++k) intersectf |= intersect[k] = matches[k] & labels[j][k]; if (!intersectf) continue; /* It does; now find the set differences both ways. */ leftoversf = matchesf = 0; - for (k = 0; k < CHARCLASS_INTS; ++k) + for (k = 0; k < CHARCLASS_WORDS; ++k) { /* Even an optimizing compiler can't know this for sure. */ - int match = matches[k], label = labels[j][k]; + charclass_word match = matches[k], label = labels[j][k]; leftoversf |= leftovers[k] = ~match & label; matchesf |= matches[k] = match & ~label; @@ -2819,10 +2845,11 @@ dfastate (state_num s, struct dfa *d, state_num trans[]) /* If we are building a searching matcher, throw in the positions of state 0 as well. */ - if (d->searchflag - && (!MBS_SUPPORT || (!d->multibyte || !next_isnt_1st_byte))) - for (j = 0; j < d->states[0].elems.nelem; ++j) - insert (d->states[0].elems.elems[j], &follows); + if (d->searchflag && (!d->multibyte || !next_isnt_1st_byte)) + { + merge (&d->states[0].elems, &follows, &tmp); + copy (&tmp, &follows); + } /* Find out if the new state will want any context information. */ possible_contexts = charclass_context (labels[i]); @@ -2843,11 +2870,11 @@ dfastate (state_num s, struct dfa *d, state_num trans[]) state_letter = state; /* Set the transitions for each character in the current label. */ - for (j = 0; j < CHARCLASS_INTS; ++j) - for (k = 0; k < INTBITS; ++k) - if (labels[i][j] & 1U << k) + for (j = 0; j < CHARCLASS_WORDS; ++j) + for (k = 0; k < CHARCLASS_WORD_BITS; ++k) + if (labels[i][j] >> k & 1) { - int c = j * INTBITS + k; + int c = j * CHARCLASS_WORD_BITS + k; if (c == eolbyte) trans[c] = state_newline; @@ -3020,7 +3047,7 @@ transit_state_singlebyte (struct dfa *d, state_num s, unsigned char const *p, match, in bytes. POS is the position of the ".". */ static int match_anychar (struct dfa *d, state_num s, position pos, - wchar_t wc, size_t mbclen) + wint_t wc, size_t mbclen) { int context; @@ -3035,6 +3062,8 @@ match_anychar (struct dfa *d, state_num s, position pos, if (syntax_bits & RE_DOT_NOT_NULL) return 0; } + else if (wc == WEOF) + return 0; context = wchar_context (wc); if (!SUCCEEDS_IN_CONTEXT (pos.constraint, d->states[s].context, context)) @@ -3048,7 +3077,7 @@ match_anychar (struct dfa *d, state_num s, position pos, POS is the position of the bracket expression. */ static int match_mb_charset (struct dfa *d, state_num s, position pos, - char const *p, wchar_t wc, size_t match_len) + char const *p, wint_t wc, size_t match_len) { size_t i; bool match; /* Matching succeeded. */ @@ -3071,6 +3100,8 @@ match_mb_charset (struct dfa *d, state_num s, position pos, if (syntax_bits & RE_DOT_NOT_NULL) return 0; } + else if (wc == WEOF) + return 0; context = wchar_context (wc); if (!SUCCEEDS_IN_CONTEXT (pos.constraint, d->states[s].context, context)) @@ -3149,7 +3180,7 @@ charset_matched: The caller MUST free the array which this function return. */ static int * check_matching_with_multibyte_ops (struct dfa *d, state_num s, - char const *p, wchar_t wc, size_t mbclen) + char const *p, wint_t wc, size_t mbclen) { size_t i; int *rarray; @@ -3184,7 +3215,7 @@ check_matching_with_multibyte_ops (struct dfa *d, state_num s, static status_transit_state transit_state_consume_1char (struct dfa *d, state_num s, unsigned char const **pp, - wchar_t wc, size_t mbclen, + wint_t wc, size_t mbclen, int *match_lens) { size_t i, j; @@ -3235,7 +3266,7 @@ transit_state (struct dfa *d, state_num s, unsigned char const **pp, int *match_lens = NULL; size_t nelem = d->states[s].mbps.nelem; /* Just a alias. */ unsigned char const *p1 = *pp; - wchar_t wc; + wint_t wc; if (nelem > 0) /* This state has (a) multibyte operator(s). @@ -3364,13 +3395,13 @@ dfaexec (struct dfa *d, char const *begin, char *end, state must skip the bytes that are not a single byte character nor the first byte of a multibyte character. */ - wchar_t wc; + wint_t wc; while (mbp < p) mbp += mbs_to_wchar (&wc, (char const *) mbp, end - (char const *) mbp, d); p = mbp; - if ((char *) p >= end) + if ((char *) p > end) { p = NULL; goto done; @@ -3477,24 +3508,16 @@ dfaexec (struct dfa *d, char const *begin, char *end, return (char *) p; } -/* Search through a buffer looking for a potential match for D. - Return the offset of the byte after the first potential match. - If there is no match, return (size_t) -1. If D lacks a superset - so it's not known whether there is a match, return (size_t) -2. - BEGIN points to the beginning of the buffer, and END points to the - first byte after its end. Store a sentinel byte (usually newline) - in *END, so the actual buffer must be one byte longer. If COUNT is - non-NULL, increment *COUNT once for each newline processed. */ -size_t -dfahint (struct dfa *d, char const *begin, char *end, size_t *count) +struct dfa * +dfasuperset (struct dfa const *d) { - if (! d->superset) - return -2; - else - { - char const *match = dfaexec (d->superset, begin, end, 1, count, NULL); - return match ? match - begin : -1; - } + return d->superset; +} + +bool +dfaisfast (struct dfa const *d) +{ + return d->fast; } static void @@ -3534,12 +3557,14 @@ dfainit (struct dfa *d) { memset (d, 0, sizeof *d); d->multibyte = MB_CUR_MAX > 1; + d->fast = !d->multibyte; } static void dfaoptimize (struct dfa *d) { size_t i; + bool have_backref = false; if (!MBS_SUPPORT || !using_utf8 ()) return; @@ -3551,6 +3576,9 @@ dfaoptimize (struct dfa *d) case ANYCHAR: /* Lowered. */ abort (); + case BACKREF: + have_backref = true; + break; case MBCSET: /* Requires multi-byte algorithm. */ return; @@ -3559,12 +3587,20 @@ dfaoptimize (struct dfa *d) } } + if (!have_backref && d->superset) + { + /* The superset DFA is not likely to be much faster, so remove it. */ + dfafree (d->superset); + free (d->superset); + d->superset = NULL; + } + free_mbdata (d); d->multibyte = false; } static void -dfasuperset (struct dfa *d) +dfassbuild (struct dfa *d) { size_t i, j; charclass ccl; @@ -3616,8 +3652,11 @@ dfasuperset (struct dfa *d) case NOTLIMWORD: if (d->multibyte) { - /* Ignore these constraints. */ + /* These constraints aren't supported in a multibyte locale. + Ignore them in the superset DFA, and treat them as + backreferences in the main DFA. */ sup->tokens[j++] = EMPTY; + d->tokens[i] = BACKREF; break; } default: @@ -3647,11 +3686,14 @@ dfacomp (char const *s, size_t len, struct dfa *d, int searchflag) dfambcache (d); dfaparse (s, len, d); dfamust (d); + dfassbuild (d); dfaoptimize (d); - dfasuperset (d); dfaanalyze (d, searchflag); if (d->superset) - dfaanalyze (d->superset, searchflag); + { + d->fast = true; + dfaanalyze (d->superset, searchflag); + } } /* Free the storage held by the components of a dfa. */ @@ -75,16 +75,14 @@ extern void dfacomp (char const *, size_t, struct dfa *, int); extern char *dfaexec (struct dfa *d, char const *begin, char *end, int newline, size_t *count, int *backref); -/* Search through a buffer looking for a potential match for D. - Return the offset of the byte after the first potential match. - If there is no match, return (size_t) -1. If D lacks a superset - so it's not known whether there is a match, return (size_t) -2. - BEGIN points to the beginning of the buffer, and END points to the - first byte after its end. Store a sentinel byte (usually newline) - in *END, so the actual buffer must be one byte longer. If COUNT is - non-NULL, increment *COUNT once for each newline processed. */ -extern size_t dfahint (struct dfa *d, char const *begin, char *end, - size_t *count); +/* Return a superset for D. The superset matches everything that D + matches, along with some other strings (though the latter should be + rare, for efficiency reasons). Return a null pointer if no useful + superset is available. */ +extern struct dfa *dfasuperset (struct dfa const *d) _GL_ATTRIBUTE_PURE; + +/* The DFA is likely to be fast. */ +extern bool dfaisfast (struct dfa const *) _GL_ATTRIBUTE_PURE; /* Free the storage held by the components of a struct dfa. */ extern void dfafree (struct dfa *); diff --git a/doc/ChangeLog b/doc/ChangeLog index b9909498..167bb9fe 100644 --- a/doc/ChangeLog +++ b/doc/ChangeLog @@ -1,3 +1,7 @@ +2014-05-14 Arnold D. Robbins <arnold@skeeve.com> + + * gawktexi.in: Fix real preface for docbook. + 2014-05-13 Arnold D. Robbins <arnold@skeeve.com> * gawktexi.in: Complete formatting for FOR_PRINT and not FOR_PRINT. diff --git a/doc/gawk.info b/doc/gawk.info index 1824c649..4c824f32 100644 --- a/doc/gawk.info +++ b/doc/gawk.info @@ -1300,12 +1300,6 @@ also must acknowledge my gratitude to G-d, for the many opportunities He has sent my way, as well as for the gifts He has given me with which to take advantage of those opportunities. - -Arnold Robbins -Nof Ayalon -ISRAEL -May, 2014 - File: gawk.info, Node: Getting Started, Next: Invoking Gawk, Prev: Preface, Up: Top @@ -33227,518 +33221,518 @@ Ref: Manual History-Footnote-164040 Ref: Manual History-Footnote-264081 Node: How To Contribute64155 Node: Acknowledgments65394 -Node: Getting Started69588 -Node: Running gawk71967 -Node: One-shot73157 -Node: Read Terminal74382 -Ref: Read Terminal-Footnote-176032 -Ref: Read Terminal-Footnote-276308 -Node: Long76479 -Node: Executable Scripts77855 -Ref: Executable Scripts-Footnote-179688 -Ref: Executable Scripts-Footnote-279790 -Node: Comments80337 -Node: Quoting82804 -Node: DOS Quoting88120 -Node: Sample Data Files88795 -Node: Very Simple91310 -Node: Two Rules95960 -Node: More Complex97855 -Ref: More Complex-Footnote-1100787 -Node: Statements/Lines100872 -Ref: Statements/Lines-Footnote-1105327 -Node: Other Features105592 -Node: When106520 -Node: Invoking Gawk108668 -Node: Command Line110131 -Node: Options110914 -Ref: Options-Footnote-1126726 -Node: Other Arguments126751 -Node: Naming Standard Input129413 -Node: Environment Variables130507 -Node: AWKPATH Variable131065 -Ref: AWKPATH Variable-Footnote-1133843 -Ref: AWKPATH Variable-Footnote-2133888 -Node: AWKLIBPATH Variable134148 -Node: Other Environment Variables134907 -Node: Exit Status138562 -Node: Include Files139237 -Node: Loading Shared Libraries142815 -Node: Obsolete144198 -Node: Undocumented144895 -Node: Regexp145137 -Node: Regexp Usage146526 -Node: Escape Sequences148559 -Node: Regexp Operators154226 -Ref: Regexp Operators-Footnote-1161706 -Ref: Regexp Operators-Footnote-2161853 -Node: Bracket Expressions161951 -Ref: table-char-classes163841 -Node: GNU Regexp Operators166364 -Node: Case-sensitivity170087 -Ref: Case-sensitivity-Footnote-1172979 -Ref: Case-sensitivity-Footnote-2173214 -Node: Leftmost Longest173322 -Node: Computed Regexps174523 -Node: Reading Files177872 -Node: Records179874 -Node: awk split records180609 -Node: gawk split records185467 -Ref: gawk split records-Footnote-1189988 -Node: Fields190025 -Ref: Fields-Footnote-1192989 -Node: Nonconstant Fields193075 -Ref: Nonconstant Fields-Footnote-1195305 -Node: Changing Fields195507 -Node: Field Separators201461 -Node: Default Field Splitting204163 -Node: Regexp Field Splitting205280 -Node: Single Character Fields208621 -Node: Command Line Field Separator209680 -Node: Full Line Fields213022 -Ref: Full Line Fields-Footnote-1213530 -Node: Field Splitting Summary213576 -Ref: Field Splitting Summary-Footnote-1216675 -Node: Constant Size216776 -Node: Splitting By Content221383 -Ref: Splitting By Content-Footnote-1225133 -Node: Multiple Line225173 -Ref: Multiple Line-Footnote-1231029 -Node: Getline231208 -Node: Plain Getline233424 -Node: Getline/Variable235519 -Node: Getline/File236666 -Node: Getline/Variable/File238050 -Ref: Getline/Variable/File-Footnote-1239649 -Node: Getline/Pipe239736 -Node: Getline/Variable/Pipe242435 -Node: Getline/Coprocess243542 -Node: Getline/Variable/Coprocess244794 -Node: Getline Notes245531 -Node: Getline Summary248335 -Ref: table-getline-variants248743 -Node: Read Timeout249655 -Ref: Read Timeout-Footnote-1253482 -Node: Command line directories253540 -Node: Printing254422 -Node: Print256053 -Node: Print Examples257394 -Node: Output Separators260173 -Node: OFMT262189 -Node: Printf263547 -Node: Basic Printf264453 -Node: Control Letters265992 -Node: Format Modifiers269846 -Node: Printf Examples275873 -Node: Redirection278580 -Node: Special Files285552 -Node: Special FD286085 -Ref: Special FD-Footnote-1289709 -Node: Special Network289783 -Node: Special Caveats290633 -Node: Close Files And Pipes291429 -Ref: Close Files And Pipes-Footnote-1298567 -Ref: Close Files And Pipes-Footnote-2298715 -Node: Expressions298865 -Node: Values299997 -Node: Constants300673 -Node: Scalar Constants301353 -Ref: Scalar Constants-Footnote-1302212 -Node: Nondecimal-numbers302462 -Node: Regexp Constants305462 -Node: Using Constant Regexps305937 -Node: Variables309007 -Node: Using Variables309662 -Node: Assignment Options311386 -Node: Conversion313261 -Ref: table-locale-affects318697 -Ref: Conversion-Footnote-1319321 -Node: All Operators319430 -Node: Arithmetic Ops320060 -Node: Concatenation322565 -Ref: Concatenation-Footnote-1325361 -Node: Assignment Ops325481 -Ref: table-assign-ops330464 -Node: Increment Ops331781 -Node: Truth Values and Conditions335219 -Node: Truth Values336302 -Node: Typing and Comparison337351 -Node: Variable Typing338144 -Ref: Variable Typing-Footnote-1342044 -Node: Comparison Operators342166 -Ref: table-relational-ops342576 -Node: POSIX String Comparison346124 -Ref: POSIX String Comparison-Footnote-1347208 -Node: Boolean Ops347346 -Ref: Boolean Ops-Footnote-1351416 -Node: Conditional Exp351507 -Node: Function Calls353234 -Node: Precedence356992 -Node: Locales360661 -Node: Patterns and Actions362264 -Node: Pattern Overview363318 -Node: Regexp Patterns364995 -Node: Expression Patterns365538 -Node: Ranges369319 -Node: BEGIN/END372425 -Node: Using BEGIN/END373187 -Ref: Using BEGIN/END-Footnote-1375923 -Node: I/O And BEGIN/END376029 -Node: BEGINFILE/ENDFILE378314 -Node: Empty381250 -Node: Using Shell Variables381567 -Node: Action Overview383850 -Node: Statements386195 -Node: If Statement388049 -Node: While Statement389548 -Node: Do Statement391592 -Node: For Statement392748 -Node: Switch Statement395900 -Node: Break Statement398003 -Node: Continue Statement400058 -Node: Next Statement401851 -Node: Nextfile Statement404241 -Node: Exit Statement406896 -Node: Built-in Variables409298 -Node: User-modified410394 -Ref: User-modified-Footnote-1418079 -Node: Auto-set418141 -Ref: Auto-set-Footnote-1431043 -Ref: Auto-set-Footnote-2431248 -Node: ARGC and ARGV431304 -Node: Arrays435158 -Node: Array Basics436656 -Node: Array Intro437482 -Ref: figure-array-elements439455 -Node: Reference to Elements441862 -Node: Assigning Elements444135 -Node: Array Example444626 -Node: Scanning an Array446358 -Node: Controlling Scanning449373 -Ref: Controlling Scanning-Footnote-1454546 -Node: Delete454862 -Ref: Delete-Footnote-1457627 -Node: Numeric Array Subscripts457684 -Node: Uninitialized Subscripts459867 -Node: Multidimensional461492 -Node: Multiscanning464585 -Node: Arrays of Arrays466174 -Node: Functions470814 -Node: Built-in471633 -Node: Calling Built-in472711 -Node: Numeric Functions474699 -Ref: Numeric Functions-Footnote-1478533 -Ref: Numeric Functions-Footnote-2478890 -Ref: Numeric Functions-Footnote-3478938 -Node: String Functions479207 -Ref: String Functions-Footnote-1502218 -Ref: String Functions-Footnote-2502347 -Ref: String Functions-Footnote-3502595 -Node: Gory Details502682 -Ref: table-sub-escapes504351 -Ref: table-sub-posix-92505705 -Ref: table-sub-proposed507056 -Ref: table-posix-sub508410 -Ref: table-gensub-escapes509955 -Ref: Gory Details-Footnote-1511131 -Ref: Gory Details-Footnote-2511182 -Node: I/O Functions511333 -Ref: I/O Functions-Footnote-1518456 -Node: Time Functions518603 -Ref: Time Functions-Footnote-1529067 -Ref: Time Functions-Footnote-2529135 -Ref: Time Functions-Footnote-3529293 -Ref: Time Functions-Footnote-4529404 -Ref: Time Functions-Footnote-5529516 -Ref: Time Functions-Footnote-6529743 -Node: Bitwise Functions530009 -Ref: table-bitwise-ops530571 -Ref: Bitwise Functions-Footnote-1534816 -Node: Type Functions535000 -Node: I18N Functions536142 -Node: User-defined537787 -Node: Definition Syntax538591 -Ref: Definition Syntax-Footnote-1543506 -Node: Function Example543575 -Ref: Function Example-Footnote-1546219 -Node: Function Caveats546241 -Node: Calling A Function546759 -Node: Variable Scope547714 -Node: Pass By Value/Reference550702 -Node: Return Statement554210 -Node: Dynamic Typing557192 -Node: Indirect Calls558121 -Node: Library Functions567808 -Ref: Library Functions-Footnote-1571321 -Ref: Library Functions-Footnote-2571464 -Node: Library Names571635 -Ref: Library Names-Footnote-1575108 -Ref: Library Names-Footnote-2575328 -Node: General Functions575414 -Node: Strtonum Function576442 -Node: Assert Function579372 -Node: Round Function582698 -Node: Cliff Random Function584239 -Node: Ordinal Functions585255 -Ref: Ordinal Functions-Footnote-1588332 -Ref: Ordinal Functions-Footnote-2588584 -Node: Join Function588795 -Ref: Join Function-Footnote-1590566 -Node: Getlocaltime Function590766 -Node: Readfile Function594507 -Node: Data File Management596346 -Node: Filetrans Function596978 -Node: Rewind Function601047 -Node: File Checking602434 -Node: Empty Files603528 -Node: Ignoring Assigns605758 -Node: Getopt Function607312 -Ref: Getopt Function-Footnote-1618615 -Node: Passwd Functions618818 -Ref: Passwd Functions-Footnote-1627796 -Node: Group Functions627884 -Node: Walking Arrays635968 -Node: Sample Programs638104 -Node: Running Examples638778 -Node: Clones639506 -Node: Cut Program640730 -Node: Egrep Program650581 -Ref: Egrep Program-Footnote-1658354 -Node: Id Program658464 -Node: Split Program662113 -Ref: Split Program-Footnote-1665632 -Node: Tee Program665760 -Node: Uniq Program668563 -Node: Wc Program675992 -Ref: Wc Program-Footnote-1680258 -Ref: Wc Program-Footnote-2680458 -Node: Miscellaneous Programs680550 -Node: Dupword Program681738 -Node: Alarm Program683769 -Node: Translate Program688576 -Ref: Translate Program-Footnote-1692963 -Ref: Translate Program-Footnote-2693211 -Node: Labels Program693345 -Ref: Labels Program-Footnote-1696716 -Node: Word Sorting696800 -Node: History Sorting700684 -Node: Extract Program702523 -Ref: Extract Program-Footnote-1710026 -Node: Simple Sed710154 -Node: Igawk Program713216 -Ref: Igawk Program-Footnote-1728387 -Ref: Igawk Program-Footnote-2728588 -Node: Anagram Program728726 -Node: Signature Program731794 -Node: Advanced Features732894 -Node: Nondecimal Data734780 -Node: Array Sorting736363 -Node: Controlling Array Traversal737060 -Node: Array Sorting Functions745344 -Ref: Array Sorting Functions-Footnote-1749213 -Node: Two-way I/O749407 -Ref: Two-way I/O-Footnote-1754839 -Node: TCP/IP Networking754921 -Node: Profiling757765 -Node: Internationalization765268 -Node: I18N and L10N766693 -Node: Explaining gettext767379 -Ref: Explaining gettext-Footnote-1772447 -Ref: Explaining gettext-Footnote-2772631 -Node: Programmer i18n772796 -Node: Translator i18n777023 -Node: String Extraction777817 -Ref: String Extraction-Footnote-1778778 -Node: Printf Ordering778864 -Ref: Printf Ordering-Footnote-1781646 -Node: I18N Portability781710 -Ref: I18N Portability-Footnote-1784159 -Node: I18N Example784222 -Ref: I18N Example-Footnote-1786860 -Node: Gawk I18N786932 -Node: Debugger787553 -Node: Debugging788524 -Node: Debugging Concepts788957 -Node: Debugging Terms790813 -Node: Awk Debugging793410 -Node: Sample Debugging Session794302 -Node: Debugger Invocation794822 -Node: Finding The Bug796155 -Node: List of Debugger Commands802642 -Node: Breakpoint Control803976 -Node: Debugger Execution Control807640 -Node: Viewing And Changing Data811000 -Node: Execution Stack814356 -Node: Debugger Info815823 -Node: Miscellaneous Debugger Commands819817 -Node: Readline Support824995 -Node: Limitations825826 -Node: Arbitrary Precision Arithmetic828078 -Ref: Arbitrary Precision Arithmetic-Footnote-1829727 -Node: General Arithmetic829875 -Node: Floating Point Issues831595 -Node: String Conversion Precision832476 -Ref: String Conversion Precision-Footnote-1834181 -Node: Unexpected Results834290 -Node: POSIX Floating Point Problems836443 -Ref: POSIX Floating Point Problems-Footnote-1840268 -Node: Integer Programming840306 -Node: Floating-point Programming842045 -Ref: Floating-point Programming-Footnote-1848376 -Ref: Floating-point Programming-Footnote-2848646 -Node: Floating-point Representation848910 -Node: Floating-point Context850075 -Ref: table-ieee-formats850914 -Node: Rounding Mode852298 -Ref: table-rounding-modes852777 -Ref: Rounding Mode-Footnote-1855792 -Node: Gawk and MPFR855971 -Node: Arbitrary Precision Floats857380 -Ref: Arbitrary Precision Floats-Footnote-1859823 -Node: Setting Precision860139 -Ref: table-predefined-precision-strings860825 -Node: Setting Rounding Mode862970 -Ref: table-gawk-rounding-modes863374 -Node: Floating-point Constants864561 -Node: Changing Precision865990 -Ref: Changing Precision-Footnote-1867387 -Node: Exact Arithmetic867561 -Node: Arbitrary Precision Integers870699 -Ref: Arbitrary Precision Integers-Footnote-1873714 -Node: Dynamic Extensions873861 -Node: Extension Intro875319 -Node: Plugin License876584 -Node: Extension Mechanism Outline877269 -Ref: load-extension877686 -Ref: load-new-function879164 -Ref: call-new-function880159 -Node: Extension API Description882174 -Node: Extension API Functions Introduction883461 -Node: General Data Types888388 -Ref: General Data Types-Footnote-1894083 -Node: Requesting Values894382 -Ref: table-value-types-returned895119 -Node: Memory Allocation Functions896073 -Ref: Memory Allocation Functions-Footnote-1898819 -Node: Constructor Functions898915 -Node: Registration Functions900673 -Node: Extension Functions901358 -Node: Exit Callback Functions903660 -Node: Extension Version String904909 -Node: Input Parsers905559 -Node: Output Wrappers915316 -Node: Two-way processors919826 -Node: Printing Messages922034 -Ref: Printing Messages-Footnote-1923111 -Node: Updating `ERRNO'923263 -Node: Accessing Parameters924002 -Node: Symbol Table Access925232 -Node: Symbol table by name925746 -Node: Symbol table by cookie927722 -Ref: Symbol table by cookie-Footnote-1931854 -Node: Cached values931917 -Ref: Cached values-Footnote-1935407 -Node: Array Manipulation935498 -Ref: Array Manipulation-Footnote-1936596 -Node: Array Data Types936635 -Ref: Array Data Types-Footnote-1939338 -Node: Array Functions939430 -Node: Flattening Arrays943266 -Node: Creating Arrays950118 -Node: Extension API Variables954843 -Node: Extension Versioning955479 -Node: Extension API Informational Variables957380 -Node: Extension API Boilerplate958466 -Node: Finding Extensions962270 -Node: Extension Example962830 -Node: Internal File Description963560 -Node: Internal File Ops967651 -Ref: Internal File Ops-Footnote-1979160 -Node: Using Internal File Ops979300 -Ref: Using Internal File Ops-Footnote-1981647 -Node: Extension Samples981913 -Node: Extension Sample File Functions983437 -Node: Extension Sample Fnmatch991924 -Node: Extension Sample Fork993693 -Node: Extension Sample Inplace994906 -Node: Extension Sample Ord996684 -Node: Extension Sample Readdir997520 -Node: Extension Sample Revout999052 -Node: Extension Sample Rev2way999645 -Node: Extension Sample Read write array1000335 -Node: Extension Sample Readfile1002218 -Node: Extension Sample API Tests1003318 -Node: Extension Sample Time1003843 -Node: gawkextlib1005207 -Node: Language History1007988 -Node: V7/SVR3.11009581 -Node: SVR41011901 -Node: POSIX1013343 -Node: BTL1014729 -Node: POSIX/GNU1015463 -Node: Feature History1021062 -Node: Common Extensions1034038 -Node: Ranges and Locales1035350 -Ref: Ranges and Locales-Footnote-11039967 -Ref: Ranges and Locales-Footnote-21039994 -Ref: Ranges and Locales-Footnote-31040228 -Node: Contributors1040449 -Node: Installation1045830 -Node: Gawk Distribution1046724 -Node: Getting1047208 -Node: Extracting1048034 -Node: Distribution contents1049726 -Node: Unix Installation1055447 -Node: Quick Installation1056064 -Node: Additional Configuration Options1058510 -Node: Configuration Philosophy1060246 -Node: Non-Unix Installation1062600 -Node: PC Installation1063058 -Node: PC Binary Installation1064369 -Node: PC Compiling1066217 -Node: PC Testing1069177 -Node: PC Using1070353 -Node: Cygwin1074521 -Node: MSYS1075330 -Node: VMS Installation1075844 -Node: VMS Compilation1076640 -Ref: VMS Compilation-Footnote-11077892 -Node: VMS Dynamic Extensions1077950 -Node: VMS Installation Details1079323 -Node: VMS Running1081574 -Node: VMS GNV1084408 -Node: VMS Old Gawk1085131 -Node: Bugs1085601 -Node: Other Versions1089519 -Node: Notes1095603 -Node: Compatibility Mode1096403 -Node: Additions1097186 -Node: Accessing The Source1098113 -Node: Adding Code1099553 -Node: New Ports1105598 -Node: Derived Files1109733 -Ref: Derived Files-Footnote-11115054 -Ref: Derived Files-Footnote-21115088 -Ref: Derived Files-Footnote-31115688 -Node: Future Extensions1115786 -Node: Implementation Limitations1116369 -Node: Extension Design1117617 -Node: Old Extension Problems1118771 -Ref: Old Extension Problems-Footnote-11120279 -Node: Extension New Mechanism Goals1120336 -Ref: Extension New Mechanism Goals-Footnote-11123701 -Node: Extension Other Design Decisions1123887 -Node: Extension Future Growth1125993 -Node: Old Extension Mechanism1126829 -Node: Basic Concepts1128569 -Node: Basic High Level1129250 -Ref: figure-general-flow1129522 -Ref: figure-process-flow1130121 -Ref: Basic High Level-Footnote-11133350 -Node: Basic Data Typing1133535 -Node: Glossary1136890 -Node: Copying1162121 -Node: GNU Free Documentation License1199677 -Node: Index1224813 +Node: Getting Started69543 +Node: Running gawk71922 +Node: One-shot73112 +Node: Read Terminal74337 +Ref: Read Terminal-Footnote-175987 +Ref: Read Terminal-Footnote-276263 +Node: Long76434 +Node: Executable Scripts77810 +Ref: Executable Scripts-Footnote-179643 +Ref: Executable Scripts-Footnote-279745 +Node: Comments80292 +Node: Quoting82759 +Node: DOS Quoting88075 +Node: Sample Data Files88750 +Node: Very Simple91265 +Node: Two Rules95915 +Node: More Complex97810 +Ref: More Complex-Footnote-1100742 +Node: Statements/Lines100827 +Ref: Statements/Lines-Footnote-1105282 +Node: Other Features105547 +Node: When106475 +Node: Invoking Gawk108623 +Node: Command Line110086 +Node: Options110869 +Ref: Options-Footnote-1126681 +Node: Other Arguments126706 +Node: Naming Standard Input129368 +Node: Environment Variables130462 +Node: AWKPATH Variable131020 +Ref: AWKPATH Variable-Footnote-1133798 +Ref: AWKPATH Variable-Footnote-2133843 +Node: AWKLIBPATH Variable134103 +Node: Other Environment Variables134862 +Node: Exit Status138517 +Node: Include Files139192 +Node: Loading Shared Libraries142770 +Node: Obsolete144153 +Node: Undocumented144850 +Node: Regexp145092 +Node: Regexp Usage146481 +Node: Escape Sequences148514 +Node: Regexp Operators154181 +Ref: Regexp Operators-Footnote-1161661 +Ref: Regexp Operators-Footnote-2161808 +Node: Bracket Expressions161906 +Ref: table-char-classes163796 +Node: GNU Regexp Operators166319 +Node: Case-sensitivity170042 +Ref: Case-sensitivity-Footnote-1172934 +Ref: Case-sensitivity-Footnote-2173169 +Node: Leftmost Longest173277 +Node: Computed Regexps174478 +Node: Reading Files177827 +Node: Records179829 +Node: awk split records180564 +Node: gawk split records185422 +Ref: gawk split records-Footnote-1189943 +Node: Fields189980 +Ref: Fields-Footnote-1192944 +Node: Nonconstant Fields193030 +Ref: Nonconstant Fields-Footnote-1195260 +Node: Changing Fields195462 +Node: Field Separators201416 +Node: Default Field Splitting204118 +Node: Regexp Field Splitting205235 +Node: Single Character Fields208576 +Node: Command Line Field Separator209635 +Node: Full Line Fields212977 +Ref: Full Line Fields-Footnote-1213485 +Node: Field Splitting Summary213531 +Ref: Field Splitting Summary-Footnote-1216630 +Node: Constant Size216731 +Node: Splitting By Content221338 +Ref: Splitting By Content-Footnote-1225088 +Node: Multiple Line225128 +Ref: Multiple Line-Footnote-1230984 +Node: Getline231163 +Node: Plain Getline233379 +Node: Getline/Variable235474 +Node: Getline/File236621 +Node: Getline/Variable/File238005 +Ref: Getline/Variable/File-Footnote-1239604 +Node: Getline/Pipe239691 +Node: Getline/Variable/Pipe242390 +Node: Getline/Coprocess243497 +Node: Getline/Variable/Coprocess244749 +Node: Getline Notes245486 +Node: Getline Summary248290 +Ref: table-getline-variants248698 +Node: Read Timeout249610 +Ref: Read Timeout-Footnote-1253437 +Node: Command line directories253495 +Node: Printing254377 +Node: Print256008 +Node: Print Examples257349 +Node: Output Separators260128 +Node: OFMT262144 +Node: Printf263502 +Node: Basic Printf264408 +Node: Control Letters265947 +Node: Format Modifiers269801 +Node: Printf Examples275828 +Node: Redirection278535 +Node: Special Files285507 +Node: Special FD286040 +Ref: Special FD-Footnote-1289664 +Node: Special Network289738 +Node: Special Caveats290588 +Node: Close Files And Pipes291384 +Ref: Close Files And Pipes-Footnote-1298522 +Ref: Close Files And Pipes-Footnote-2298670 +Node: Expressions298820 +Node: Values299952 +Node: Constants300628 +Node: Scalar Constants301308 +Ref: Scalar Constants-Footnote-1302167 +Node: Nondecimal-numbers302417 +Node: Regexp Constants305417 +Node: Using Constant Regexps305892 +Node: Variables308962 +Node: Using Variables309617 +Node: Assignment Options311341 +Node: Conversion313216 +Ref: table-locale-affects318652 +Ref: Conversion-Footnote-1319276 +Node: All Operators319385 +Node: Arithmetic Ops320015 +Node: Concatenation322520 +Ref: Concatenation-Footnote-1325316 +Node: Assignment Ops325436 +Ref: table-assign-ops330419 +Node: Increment Ops331736 +Node: Truth Values and Conditions335174 +Node: Truth Values336257 +Node: Typing and Comparison337306 +Node: Variable Typing338099 +Ref: Variable Typing-Footnote-1341999 +Node: Comparison Operators342121 +Ref: table-relational-ops342531 +Node: POSIX String Comparison346079 +Ref: POSIX String Comparison-Footnote-1347163 +Node: Boolean Ops347301 +Ref: Boolean Ops-Footnote-1351371 +Node: Conditional Exp351462 +Node: Function Calls353189 +Node: Precedence356947 +Node: Locales360616 +Node: Patterns and Actions362219 +Node: Pattern Overview363273 +Node: Regexp Patterns364950 +Node: Expression Patterns365493 +Node: Ranges369274 +Node: BEGIN/END372380 +Node: Using BEGIN/END373142 +Ref: Using BEGIN/END-Footnote-1375878 +Node: I/O And BEGIN/END375984 +Node: BEGINFILE/ENDFILE378269 +Node: Empty381205 +Node: Using Shell Variables381522 +Node: Action Overview383805 +Node: Statements386150 +Node: If Statement388004 +Node: While Statement389503 +Node: Do Statement391547 +Node: For Statement392703 +Node: Switch Statement395855 +Node: Break Statement397958 +Node: Continue Statement400013 +Node: Next Statement401806 +Node: Nextfile Statement404196 +Node: Exit Statement406851 +Node: Built-in Variables409253 +Node: User-modified410349 +Ref: User-modified-Footnote-1418034 +Node: Auto-set418096 +Ref: Auto-set-Footnote-1430998 +Ref: Auto-set-Footnote-2431203 +Node: ARGC and ARGV431259 +Node: Arrays435113 +Node: Array Basics436611 +Node: Array Intro437437 +Ref: figure-array-elements439410 +Node: Reference to Elements441817 +Node: Assigning Elements444090 +Node: Array Example444581 +Node: Scanning an Array446313 +Node: Controlling Scanning449328 +Ref: Controlling Scanning-Footnote-1454501 +Node: Delete454817 +Ref: Delete-Footnote-1457582 +Node: Numeric Array Subscripts457639 +Node: Uninitialized Subscripts459822 +Node: Multidimensional461447 +Node: Multiscanning464540 +Node: Arrays of Arrays466129 +Node: Functions470769 +Node: Built-in471588 +Node: Calling Built-in472666 +Node: Numeric Functions474654 +Ref: Numeric Functions-Footnote-1478488 +Ref: Numeric Functions-Footnote-2478845 +Ref: Numeric Functions-Footnote-3478893 +Node: String Functions479162 +Ref: String Functions-Footnote-1502173 +Ref: String Functions-Footnote-2502302 +Ref: String Functions-Footnote-3502550 +Node: Gory Details502637 +Ref: table-sub-escapes504306 +Ref: table-sub-posix-92505660 +Ref: table-sub-proposed507011 +Ref: table-posix-sub508365 +Ref: table-gensub-escapes509910 +Ref: Gory Details-Footnote-1511086 +Ref: Gory Details-Footnote-2511137 +Node: I/O Functions511288 +Ref: I/O Functions-Footnote-1518411 +Node: Time Functions518558 +Ref: Time Functions-Footnote-1529022 +Ref: Time Functions-Footnote-2529090 +Ref: Time Functions-Footnote-3529248 +Ref: Time Functions-Footnote-4529359 +Ref: Time Functions-Footnote-5529471 +Ref: Time Functions-Footnote-6529698 +Node: Bitwise Functions529964 +Ref: table-bitwise-ops530526 +Ref: Bitwise Functions-Footnote-1534771 +Node: Type Functions534955 +Node: I18N Functions536097 +Node: User-defined537742 +Node: Definition Syntax538546 +Ref: Definition Syntax-Footnote-1543461 +Node: Function Example543530 +Ref: Function Example-Footnote-1546174 +Node: Function Caveats546196 +Node: Calling A Function546714 +Node: Variable Scope547669 +Node: Pass By Value/Reference550657 +Node: Return Statement554165 +Node: Dynamic Typing557147 +Node: Indirect Calls558076 +Node: Library Functions567763 +Ref: Library Functions-Footnote-1571276 +Ref: Library Functions-Footnote-2571419 +Node: Library Names571590 +Ref: Library Names-Footnote-1575063 +Ref: Library Names-Footnote-2575283 +Node: General Functions575369 +Node: Strtonum Function576397 +Node: Assert Function579327 +Node: Round Function582653 +Node: Cliff Random Function584194 +Node: Ordinal Functions585210 +Ref: Ordinal Functions-Footnote-1588287 +Ref: Ordinal Functions-Footnote-2588539 +Node: Join Function588750 +Ref: Join Function-Footnote-1590521 +Node: Getlocaltime Function590721 +Node: Readfile Function594462 +Node: Data File Management596301 +Node: Filetrans Function596933 +Node: Rewind Function601002 +Node: File Checking602389 +Node: Empty Files603483 +Node: Ignoring Assigns605713 +Node: Getopt Function607267 +Ref: Getopt Function-Footnote-1618570 +Node: Passwd Functions618773 +Ref: Passwd Functions-Footnote-1627751 +Node: Group Functions627839 +Node: Walking Arrays635923 +Node: Sample Programs638059 +Node: Running Examples638733 +Node: Clones639461 +Node: Cut Program640685 +Node: Egrep Program650536 +Ref: Egrep Program-Footnote-1658309 +Node: Id Program658419 +Node: Split Program662068 +Ref: Split Program-Footnote-1665587 +Node: Tee Program665715 +Node: Uniq Program668518 +Node: Wc Program675947 +Ref: Wc Program-Footnote-1680213 +Ref: Wc Program-Footnote-2680413 +Node: Miscellaneous Programs680505 +Node: Dupword Program681693 +Node: Alarm Program683724 +Node: Translate Program688531 +Ref: Translate Program-Footnote-1692918 +Ref: Translate Program-Footnote-2693166 +Node: Labels Program693300 +Ref: Labels Program-Footnote-1696671 +Node: Word Sorting696755 +Node: History Sorting700639 +Node: Extract Program702478 +Ref: Extract Program-Footnote-1709981 +Node: Simple Sed710109 +Node: Igawk Program713171 +Ref: Igawk Program-Footnote-1728342 +Ref: Igawk Program-Footnote-2728543 +Node: Anagram Program728681 +Node: Signature Program731749 +Node: Advanced Features732849 +Node: Nondecimal Data734735 +Node: Array Sorting736318 +Node: Controlling Array Traversal737015 +Node: Array Sorting Functions745299 +Ref: Array Sorting Functions-Footnote-1749168 +Node: Two-way I/O749362 +Ref: Two-way I/O-Footnote-1754794 +Node: TCP/IP Networking754876 +Node: Profiling757720 +Node: Internationalization765223 +Node: I18N and L10N766648 +Node: Explaining gettext767334 +Ref: Explaining gettext-Footnote-1772402 +Ref: Explaining gettext-Footnote-2772586 +Node: Programmer i18n772751 +Node: Translator i18n776978 +Node: String Extraction777772 +Ref: String Extraction-Footnote-1778733 +Node: Printf Ordering778819 +Ref: Printf Ordering-Footnote-1781601 +Node: I18N Portability781665 +Ref: I18N Portability-Footnote-1784114 +Node: I18N Example784177 +Ref: I18N Example-Footnote-1786815 +Node: Gawk I18N786887 +Node: Debugger787508 +Node: Debugging788479 +Node: Debugging Concepts788912 +Node: Debugging Terms790768 +Node: Awk Debugging793365 +Node: Sample Debugging Session794257 +Node: Debugger Invocation794777 +Node: Finding The Bug796110 +Node: List of Debugger Commands802597 +Node: Breakpoint Control803931 +Node: Debugger Execution Control807595 +Node: Viewing And Changing Data810955 +Node: Execution Stack814311 +Node: Debugger Info815778 +Node: Miscellaneous Debugger Commands819772 +Node: Readline Support824950 +Node: Limitations825781 +Node: Arbitrary Precision Arithmetic828033 +Ref: Arbitrary Precision Arithmetic-Footnote-1829682 +Node: General Arithmetic829830 +Node: Floating Point Issues831550 +Node: String Conversion Precision832431 +Ref: String Conversion Precision-Footnote-1834136 +Node: Unexpected Results834245 +Node: POSIX Floating Point Problems836398 +Ref: POSIX Floating Point Problems-Footnote-1840223 +Node: Integer Programming840261 +Node: Floating-point Programming842000 +Ref: Floating-point Programming-Footnote-1848331 +Ref: Floating-point Programming-Footnote-2848601 +Node: Floating-point Representation848865 +Node: Floating-point Context850030 +Ref: table-ieee-formats850869 +Node: Rounding Mode852253 +Ref: table-rounding-modes852732 +Ref: Rounding Mode-Footnote-1855747 +Node: Gawk and MPFR855926 +Node: Arbitrary Precision Floats857335 +Ref: Arbitrary Precision Floats-Footnote-1859778 +Node: Setting Precision860094 +Ref: table-predefined-precision-strings860780 +Node: Setting Rounding Mode862925 +Ref: table-gawk-rounding-modes863329 +Node: Floating-point Constants864516 +Node: Changing Precision865945 +Ref: Changing Precision-Footnote-1867342 +Node: Exact Arithmetic867516 +Node: Arbitrary Precision Integers870654 +Ref: Arbitrary Precision Integers-Footnote-1873669 +Node: Dynamic Extensions873816 +Node: Extension Intro875274 +Node: Plugin License876539 +Node: Extension Mechanism Outline877224 +Ref: load-extension877641 +Ref: load-new-function879119 +Ref: call-new-function880114 +Node: Extension API Description882129 +Node: Extension API Functions Introduction883416 +Node: General Data Types888343 +Ref: General Data Types-Footnote-1894038 +Node: Requesting Values894337 +Ref: table-value-types-returned895074 +Node: Memory Allocation Functions896028 +Ref: Memory Allocation Functions-Footnote-1898774 +Node: Constructor Functions898870 +Node: Registration Functions900628 +Node: Extension Functions901313 +Node: Exit Callback Functions903615 +Node: Extension Version String904864 +Node: Input Parsers905514 +Node: Output Wrappers915271 +Node: Two-way processors919781 +Node: Printing Messages921989 +Ref: Printing Messages-Footnote-1923066 +Node: Updating `ERRNO'923218 +Node: Accessing Parameters923957 +Node: Symbol Table Access925187 +Node: Symbol table by name925701 +Node: Symbol table by cookie927677 +Ref: Symbol table by cookie-Footnote-1931809 +Node: Cached values931872 +Ref: Cached values-Footnote-1935362 +Node: Array Manipulation935453 +Ref: Array Manipulation-Footnote-1936551 +Node: Array Data Types936590 +Ref: Array Data Types-Footnote-1939293 +Node: Array Functions939385 +Node: Flattening Arrays943221 +Node: Creating Arrays950073 +Node: Extension API Variables954798 +Node: Extension Versioning955434 +Node: Extension API Informational Variables957335 +Node: Extension API Boilerplate958421 +Node: Finding Extensions962225 +Node: Extension Example962785 +Node: Internal File Description963515 +Node: Internal File Ops967606 +Ref: Internal File Ops-Footnote-1979115 +Node: Using Internal File Ops979255 +Ref: Using Internal File Ops-Footnote-1981602 +Node: Extension Samples981868 +Node: Extension Sample File Functions983392 +Node: Extension Sample Fnmatch991879 +Node: Extension Sample Fork993648 +Node: Extension Sample Inplace994861 +Node: Extension Sample Ord996639 +Node: Extension Sample Readdir997475 +Node: Extension Sample Revout999007 +Node: Extension Sample Rev2way999600 +Node: Extension Sample Read write array1000290 +Node: Extension Sample Readfile1002173 +Node: Extension Sample API Tests1003273 +Node: Extension Sample Time1003798 +Node: gawkextlib1005162 +Node: Language History1007943 +Node: V7/SVR3.11009536 +Node: SVR41011856 +Node: POSIX1013298 +Node: BTL1014684 +Node: POSIX/GNU1015418 +Node: Feature History1021017 +Node: Common Extensions1033993 +Node: Ranges and Locales1035305 +Ref: Ranges and Locales-Footnote-11039922 +Ref: Ranges and Locales-Footnote-21039949 +Ref: Ranges and Locales-Footnote-31040183 +Node: Contributors1040404 +Node: Installation1045785 +Node: Gawk Distribution1046679 +Node: Getting1047163 +Node: Extracting1047989 +Node: Distribution contents1049681 +Node: Unix Installation1055402 +Node: Quick Installation1056019 +Node: Additional Configuration Options1058465 +Node: Configuration Philosophy1060201 +Node: Non-Unix Installation1062555 +Node: PC Installation1063013 +Node: PC Binary Installation1064324 +Node: PC Compiling1066172 +Node: PC Testing1069132 +Node: PC Using1070308 +Node: Cygwin1074476 +Node: MSYS1075285 +Node: VMS Installation1075799 +Node: VMS Compilation1076595 +Ref: VMS Compilation-Footnote-11077847 +Node: VMS Dynamic Extensions1077905 +Node: VMS Installation Details1079278 +Node: VMS Running1081529 +Node: VMS GNV1084363 +Node: VMS Old Gawk1085086 +Node: Bugs1085556 +Node: Other Versions1089474 +Node: Notes1095558 +Node: Compatibility Mode1096358 +Node: Additions1097141 +Node: Accessing The Source1098068 +Node: Adding Code1099508 +Node: New Ports1105553 +Node: Derived Files1109688 +Ref: Derived Files-Footnote-11115009 +Ref: Derived Files-Footnote-21115043 +Ref: Derived Files-Footnote-31115643 +Node: Future Extensions1115741 +Node: Implementation Limitations1116324 +Node: Extension Design1117572 +Node: Old Extension Problems1118726 +Ref: Old Extension Problems-Footnote-11120234 +Node: Extension New Mechanism Goals1120291 +Ref: Extension New Mechanism Goals-Footnote-11123656 +Node: Extension Other Design Decisions1123842 +Node: Extension Future Growth1125948 +Node: Old Extension Mechanism1126784 +Node: Basic Concepts1128524 +Node: Basic High Level1129205 +Ref: figure-general-flow1129477 +Ref: figure-process-flow1130076 +Ref: Basic High Level-Footnote-11133305 +Node: Basic Data Typing1133490 +Node: Glossary1136845 +Node: Copying1162076 +Node: GNU Free Documentation License1199632 +Node: Index1224768 End Tag Table diff --git a/doc/gawk.texi b/doc/gawk.texi index 10ddd235..9422f43b 100644 --- a/doc/gawk.texi +++ b/doc/gawk.texi @@ -1131,6 +1131,21 @@ March, 2001 @c @c 12/2000: Chuck wants the preface & intro combined. +@c This bit is post-processed by a script which turns the chapter +@c tag into a preface tag, and moves this stuff to before the title. +@c Bleah. +@docbook + <prefaceinfo> + <author> + <firstname>Arnold</firstname> + <surname>Robbins</surname> + <affiliation><jobtitle>Nof Ayalon</jobtitle></affiliation> + <affiliation><jobtitle>ISRAEL</jobtitle></affiliation> + </author> + <date>June, 2014</date> + </prefaceinfo> +@end docbook + Several kinds of tasks occur repeatedly when working with text files. You might want to extract certain lines and discard the rest. @@ -2022,12 +2037,14 @@ which they raised and educated me. Finally, I also must acknowledge my gratitude to G-d, for the many opportunities He has sent my way, as well as for the gifts He has given me with which to take advantage of those opportunities. +@iftex @sp 2 @noindent Arnold Robbins @* Nof Ayalon @* ISRAEL @* May, 2014 +@end iftex @ifnotinfo @part @value{PART1}The @command{awk} Language diff --git a/doc/gawktexi.in b/doc/gawktexi.in index d45cae06..2edeacc8 100644 --- a/doc/gawktexi.in +++ b/doc/gawktexi.in @@ -1126,6 +1126,21 @@ March, 2001 @c @c 12/2000: Chuck wants the preface & intro combined. +@c This bit is post-processed by a script which turns the chapter +@c tag into a preface tag, and moves this stuff to before the title. +@c Bleah. +@docbook + <prefaceinfo> + <author> + <firstname>Arnold</firstname> + <surname>Robbins</surname> + <affiliation><jobtitle>Nof Ayalon</jobtitle></affiliation> + <affiliation><jobtitle>ISRAEL</jobtitle></affiliation> + </author> + <date>June, 2014</date> + </prefaceinfo> +@end docbook + Several kinds of tasks occur repeatedly when working with text files. You might want to extract certain lines and discard the rest. @@ -1989,12 +2004,14 @@ which they raised and educated me. Finally, I also must acknowledge my gratitude to G-d, for the many opportunities He has sent my way, as well as for the gifts He has given me with which to take advantage of those opportunities. +@iftex @sp 2 @noindent Arnold Robbins @* Nof Ayalon @* ISRAEL @* May, 2014 +@end iftex @ifnotinfo @part @value{PART1}The @command{awk} Language |