Mercurial > hg > xemacs-beta
annotate lib-src/yow.c @ 4604:e0a8715fdb1f
Support new IGNORE-INVALID-SEQUENCESP argument, #'query-coding-region.
lisp/ChangeLog addition:
2009-02-07 Aidan Kehoe <kehoea@parhasard.net>
* coding.el (query-coding-clear-highlights):
Rename the BUFFER argument to BUFFER-OR-STRING, describe it as
possibly being a string in its documentation.
(default-query-coding-region):
Add a new IGNORE-INVALID-SEQUENCESP argument, document that this
function does not support it.
Bind case-fold-search to nil, we don't want this to influence what the
function thinks is encodable or not.
(query-coding-region):
Add a new IGNORE-INVALID-SEQUENCESP argument, document what it
does; reflect this new argument in the associated compiler macro.
(query-coding-string):
Add a new IGNORE-INVALID-SEQUENCESP argument, document what it
does. Support the HIGHLIGHT argument correctly.
* unicode.el (unicode-query-coding-region):
Add a new IGNORE-INVALID-SEQUENCESP argument, document what it
does, implement this. Document a potential problem.
Use #'query-coding-clear-highlights instead of reimplementing it
ourselves.
Remove some debugging messages.
* mule/arabic.el (iso-8859-6):
* mule/cyrillic.el (iso-8859-5):
* mule/greek.el (iso-8859-7):
* mule/hebrew.el (iso-8859-8):
* mule/latin.el (iso-8859-2):
* mule/latin.el (iso-8859-3):
* mule/latin.el (iso-8859-4):
* mule/latin.el (iso-8859-14):
* mule/latin.el (iso-8859-15):
* mule/latin.el (iso-8859-16):
* mule/latin.el (iso-8859-9):
* mule/latin.el (windows-1252):
* mule/mule-coding.el (iso-8859-1):
Avoid the assumption that characters not given an explicit mapping
in these coding systems map to the ISO 8859-1 characters
corresponding to the octets on disk; this makes it much more
reasonable to implement the IGNORE-INVALID-SEQUENCESP argument to
query-coding-region.
* mule/mule-cmds.el (set-language-info):
Correct the docstring.
* mule/mule-cmds.el (finish-set-language-environment):
Treat invalid Unicode sequences produced from
invalid-sequence-coding-system and corresponding to control
characters the same as control characters in redisplay.
* mule/mule-cmds.el:
Document that encode-coding-char is available in coding.el
* mule/mule-coding.el (make-8-bit-generate-helper):
Change to return the both the encode-program generated and the
relevant non-ASCII charset; update the docstring to reflect this.
* mule/mule-coding.el
(make-8-bit-generate-encode-program-and-skip-chars-strings):
Rename this function; have it return skip-chars-strings as well as
the encode program. Have these skip-chars-strings use ranges for
charsets, where possible.
* mule/mule-coding.el (make-8-bit-create-decode-encode-tables):
Revise this to allow people to specify explicitly characters that
should be undefined (= corresponding to keys in
unicode-error-default-translation-table), and treating unspecified
octets above #x7f as undefined by default.
* mule/mule-coding.el (8-bit-fixed-query-coding-region):
Add a new IGNORE-INVALID-SEQUENCESP argument, implement support
for it using the 8-bit-fixed-invalid-sequences-skip-chars coding
system property; remove some debugging messages.
* mule/mule-coding.el (make-8-bit-coding-system):
This function is dumped, autoloading it makes no sense.
Document what happens when characters above #x7f are not
specified, implement this.
* mule/vietnamese.el:
Correct spelling.
tests/ChangeLog addition:
2009-02-07 Aidan Kehoe <kehoea@parhasard.net>
* automated/query-coding-tests.el:
Add FAILING-CASE arguments to the Assert calls, making #'q-c-debug
mostly unnecessary. Remove #'q-c-debug.
Add new tests that use the IGNORE-INVALID-SEQUENCESP argument to
#'query-coding-region; rework the existing ones to respect it.
| author | Aidan Kehoe <kehoea@parhasard.net> |
|---|---|
| date | Sat, 07 Feb 2009 17:13:37 +0000 |
| parents | 943eaba38521 |
| children |
| rev | line source |
|---|---|
| 428 | 1 /* |
| 2 * yow.c | |
| 3 * | |
| 4 * Print a quotation from Zippy the Pinhead. | |
| 5 * Qux <Kaufman-David@Yale> March 6, 1986 | |
| 6 * | |
| 7 * With dynamic memory allocation. | |
| 8 */ | |
| 9 | |
| 10 /* Synched up with: FSF 19.28. */ | |
| 11 | |
| 438 | 12 #include <config.h> |
| 428 | 13 |
| 14 #include <stdio.h> | |
| 15 #include <ctype.h> | |
| 16 #include <../src/paths.h> /* For PATH_DATA. */ | |
| 17 | |
| 18 #if __STDC__ || defined(STDC_HEADERS) | |
| 19 #include <stdlib.h> | |
| 20 #include <unistd.h> | |
| 21 #include <string.h> | |
| 22 #include <time.h> /* for time() */ | |
| 23 #endif | |
| 24 | |
| 25 #define BUFSIZE 80 | |
| 26 #define SEP '\0' | |
| 27 | |
| 28 #ifndef YOW_FILE | |
| 29 #define YOW_FILE "yow.lines" | |
| 30 #endif | |
| 31 | |
| 32 void yow (FILE *fp); | |
| 33 void setup_yow (FILE *fp); | |
| 34 | |
| 442 | 35 #ifdef WIN32_NATIVE |
| 428 | 36 #define rootrelativepath(rel) \ |
| 37 ({\ | |
| 38 static char res[BUFSIZE], *p;\ | |
| 39 strcpy (res, argv[0]);\ | |
| 40 p = res + strlen (res);\ | |
| 41 while (p != res && *p != '/' && *p != '\\' && *p != ':') p--;\ | |
| 42 strcpy (p + 1, "../");\ | |
| 43 strcpy (p + 4, rel);\ | |
| 44 &res;}) | |
| 45 #endif | |
| 46 | |
| 47 int | |
| 48 main (int argc, char *argv[]) | |
| 49 { | |
| 50 FILE *fp; | |
| 51 char file[BUFSIZ]; | |
| 52 | |
| 53 if (argc > 2 && !strcmp (argv[1], "-f")) | |
| 54 strcpy (file, argv[2]); | |
| 55 else | |
| 56 #ifdef PATH_DATA | |
| 57 #ifdef vms | |
| 58 sprintf (file, "%s%s", PATH_DATA, YOW_FILE); | |
| 59 #else | |
| 60 sprintf (file, "%s/%s", PATH_DATA, YOW_FILE); | |
| 61 #endif | |
| 62 #else /* !PATH_DATA */ | |
| 63 { | |
| 64 fprintf (stderr, | |
| 65 "%s: the location of the \"%s\" file was not supplied at compile-time.\n\ | |
| 66 You must supply it with the -f command-line option.\n", | |
| 67 argv[0], YOW_FILE); | |
| 68 exit (1); | |
| 69 } | |
| 70 #endif | |
| 71 | |
| 72 if ((fp = fopen(file, "r")) == NULL) { | |
| 73 perror(file); | |
| 74 exit(1); | |
| 75 } | |
| 76 | |
| 77 /* initialize random seed */ | |
| 78 srand((int) (getpid() + time((time_t *) 0))); | |
| 79 | |
| 80 setup_yow(fp); | |
| 81 yow(fp); | |
| 82 fclose(fp); | |
| 83 return 0; | |
| 84 } | |
| 85 | |
| 86 static long len = -1; | |
| 87 static long header_len; | |
| 88 | |
| 89 #define AVG_LEN 40 /* average length of a quotation */ | |
| 90 | |
| 91 /* Sets len and header_len */ | |
| 92 void | |
| 440 | 93 setup_yow (FILE *fp) |
| 428 | 94 { |
| 95 int c; | |
| 96 | |
| 97 /* Get length of file */ | |
| 98 /* Because the header (stuff before the first SEP) can be very long, | |
| 99 * thus biasing our search in favor of the first quotation in the file, | |
| 100 * we explicitly skip that. */ | |
| 101 while ((c = getc(fp)) != SEP) { | |
| 102 if (c == EOF) { | |
| 103 fprintf(stderr, "File contains no separators.\n"); | |
| 104 exit(2); | |
| 105 } | |
| 106 } | |
| 107 header_len = ftell(fp); | |
| 108 if (header_len > AVG_LEN) | |
| 109 header_len -= AVG_LEN; /* allow the first quotation to appear */ | |
| 110 | |
| 111 if (fseek(fp, 0L, 2) == -1) { | |
| 112 perror("fseek 1"); | |
| 113 exit(1); | |
| 114 } | |
| 115 len = ftell(fp) - header_len; | |
| 116 } | |
| 117 | |
| 118 | |
| 119 /* go to a random place in the file and print the quotation there */ | |
| 120 void | |
| 440 | 121 yow (FILE *fp) |
| 428 | 122 { |
| 123 long offset; | |
| 124 int c, i = 0; | |
| 125 char *buf; | |
| 647 | 126 int bufsize; |
| 428 | 127 |
| 128 offset = rand() % len + header_len; | |
| 129 if (fseek(fp, offset, 0) == -1) { | |
| 130 perror("fseek 2"); | |
| 131 exit(1); | |
| 132 } | |
| 133 | |
| 134 /* Read until SEP, read next line, print it. | |
| 135 (Note that we will never print anything before the first separator.) | |
| 136 If we hit EOF looking for the first SEP, just recurse. */ | |
| 137 while ((c = getc(fp)) != SEP) | |
| 138 if (c == EOF) { | |
| 139 yow(fp); | |
| 140 return; | |
| 141 } | |
| 142 | |
| 143 /* Skip leading whitespace, then read in a quotation. | |
| 144 If we hit EOF before we find a non-whitespace char, recurse. */ | |
| 145 while (isspace(c = getc(fp))) | |
| 146 ; | |
| 147 if (c == EOF) { | |
| 148 yow(fp); | |
| 149 return; | |
| 150 } | |
| 151 | |
| 152 bufsize = BUFSIZE; | |
| 153 buf = (char *) malloc(bufsize); | |
| 154 if (buf == (char *)0) { | |
| 155 fprintf(stderr, "can't allocate any memory\n"); | |
| 156 exit (3); | |
| 157 } | |
| 158 | |
| 159 buf[i++] = c; | |
| 160 while ((c = getc(fp)) != SEP && c != EOF) { | |
| 161 buf[i++] = c; | |
| 162 | |
| 163 if (i == bufsize-1) { | |
| 164 /* Yow! Is this quotation too long yet? */ | |
| 165 bufsize *= 2; | |
| 166 buf = (char *)realloc(buf, bufsize); | |
| 167 if (buf == (char *)0) { | |
| 168 fprintf(stderr, "can't allocate more memory\n"); | |
| 169 exit (3); | |
| 170 } | |
| 171 } | |
| 172 } | |
| 173 buf[i++] = 0; | |
| 174 printf("%s\n", buf); | |
| 175 } | |
| 176 |