Mercurial > hg > xemacs-beta
view lib-src/b2m.c @ 4407:4ee73bbe4f8e
Always use boyer_moore in ASCII or Latin-1 buffers with ASCII search strings.
2007-12-26 Aidan Kehoe <kehoea@parhasard.net>
* casetab.c:
Extend and correct some case table documentation.
* search.c (search_buffer):
Correct a bug where only the first entry for a character in the
case equivalence table was examined in determining if the
Boyer-Moore search algorithm is appropriate.
If there are case mappings outside of the charset and row of the
characters specified in the search string, those case mappings can
be safely ignored (and Boyer-Moore search can be used) if we know
from the buffer statistics that the corresponding characters cannot
occur.
* search.c (boyer_moore):
Assert that we haven't been passed a string with varying
characters sets or rows within character sets. That's what
simple_search is for.
In the very rare event that a character in the search string has a
canonical case mapping that is not in the same character set and
row, don't try to search for the canonical character, search for
some other character that is in the the desired character set and
row. Assert that the case table isn't corrupt.
Do not search for any character case mappings that cannot possibly
occur in the buffer, given the buffer metadata about its
contents.
| author | Aidan Kehoe <kehoea@parhasard.net> |
|---|---|
| date | Wed, 26 Dec 2007 17:30:16 +0100 |
| parents | abe6d1db359e |
| children | 061f4f90f874 |
line wrap: on
line source
/* * b2m - a filter for Babyl -> Unix mail files * * usage: b2m < babyl > mailbox * * I find this useful whenever I have to use a * system which - shock horror! - doesn't run * Gnu emacs. At least now I can read all my * Gnumacs Babyl format mail files! * * it's not much but it's free! * * Ed Wilkinson * E.Wilkinson@massey.ac.nz * Mon Nov 7 15:54:06 PDT 1988 */ /* Made conformant to the GNU coding standards January, 1995 by Francesco Potorti` <pot@cnuce.cnr.it>. */ #ifdef HAVE_CONFIG_H #include <config.h> /* On some systems, Emacs defines static as nothing for the sake of unexec. We don't want that here since we don't use unexec. */ #undef static #endif #include <stdio.h> #include <stdlib.h> #include <string.h> #include <time.h> #include <sys/types.h> #ifdef WIN32_NATIVE #include <fcntl.h> #endif #undef TRUE #define TRUE 1 #undef FALSE #define FALSE 0 /* Exit codes for success and failure. */ #ifdef VMS #define GOOD 1 #define BAD 0 #else #define GOOD 0 #define BAD 1 #endif #define streq(s,t) (strcmp (s, t) == 0) #define strneq(s,t,n) (strncmp (s, t, n) == 0) typedef int logical; /* * A `struct linebuffer' is a structure which holds a line of text. * `readline' reads a line from a stream into a linebuffer and works * regardless of the length of the line. */ struct linebuffer { long size; char *buffer; }; static long *xmalloc (unsigned int); static long *xrealloc (void *, unsigned int); static char *concat (char *s1, char *s2, char *s3); static long readline (struct linebuffer *, FILE *); static void fatal (char *); /* * xnew -- allocate storage. SYNOPSIS: Type *xnew (int n, Type); */ #define xnew(n, Type) ((Type *) xmalloc ((n) * sizeof (Type))) char *progname; int main (int argc, char *argv[]) { logical labels_saved, printing, header; time_t ltoday; char *labels = NULL, *p, *today; struct linebuffer data; #ifdef WIN32_NATIVE _fmode = O_BINARY; /* all of files are treated as binary files */ if (!isatty (fileno (stdout))) setmode (fileno (stdout), O_BINARY); if (!isatty (fileno (stdin))) setmode (fileno (stdin), O_BINARY); #endif progname = argv[0]; if (argc != 1) { fprintf (stderr, "Usage: %s <babylmailbox >unixmailbox\n", progname); exit (GOOD); } labels_saved = printing = header = FALSE; ltoday = time (0); today = ctime (<oday); data.size = 200; data.buffer = xnew (200, char); if (readline (&data, stdin) == 0 || !strneq (data.buffer, "BABYL OPTIONS:", 14)) fatal ("standard input is not a Babyl mailfile."); while (readline (&data, stdin) > 0) { if (streq (data.buffer, "*** EOOH ***") && !printing) { printing = header = TRUE; printf ("From \"Babyl to mail by %s\" %s", progname, today); continue; } if (data.buffer[0] == '\037') { if (data.buffer[1] == '\0') continue; else if (data.buffer[1] == '\f') { /* Save labels. */ readline (&data, stdin); p = strtok (data.buffer, " ,\r\n\t"); labels = "X-Babyl-Labels: "; while ((p = strtok (NULL, " ,\r\n\t"))) labels = concat (labels, p, ", "); p = &labels[strlen (labels) - 2]; if (*p == ',') *p = '\0'; printing = header = FALSE; labels_saved = TRUE; continue; } } if ((data.buffer[0] == '\0') && header) { header = FALSE; if (labels_saved) puts (labels); } if (printing) puts (data.buffer); } return 0; } /* * Return a newly-allocated string whose contents * concatenate those of s1, s2, s3. */ static char * concat (char *s1, char *s2, char *s3) { int len1 = strlen (s1), len2 = strlen (s2), len3 = strlen (s3); char *result = xnew (len1 + len2 + len3 + 1, char); strcpy (result, s1); strcpy (result + len1, s2); strcpy (result + len1 + len2, s3); result[len1 + len2 + len3] = '\0'; return result; } /* * Read a line of text from `stream' into `linebuffer'. * Return the number of characters read from `stream', * which is the length of the line including the newline, if any. */ static long readline (struct linebuffer *linebuffer, FILE *stream) { char *buffer = linebuffer->buffer; register char *p = linebuffer->buffer; register char *pend; int chars_deleted; pend = p + linebuffer->size; /* Separate to avoid 386/IX compiler bug. */ while (1) { register int c = getc (stream); if (p == pend) { linebuffer->size *= 2; buffer = (char *) xrealloc (buffer, linebuffer->size); p += buffer - linebuffer->buffer; pend = buffer + linebuffer->size; linebuffer->buffer = buffer; } if (c == EOF) { chars_deleted = 0; break; } if (c == '\n') { if (p[-1] == '\r' && p > buffer) { *--p = '\0'; chars_deleted = 2; } else { *p = '\0'; chars_deleted = 1; } break; } *p++ = c; } return (p - buffer + chars_deleted); } /* * Like malloc but get fatal error if memory is exhausted. */ static long * xmalloc (unsigned int size) { long *result = (long *) malloc (size); if (result == NULL) fatal ("virtual memory exhausted"); return result; } static long * xrealloc (void *ptr, unsigned int size) { long *result = (long *) realloc (ptr, size); if (result == NULL) fatal ("virtual memory exhausted"); return result; } static void fatal (char *message) { fprintf (stderr, "%s: %s\n", progname, message); exit (BAD); }
