Skip to content

Simplest change to change from pcre to pcre2 #54

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
paulrho wants to merge 3 commits into
base: master
Choose a base branch
from
Open

Simplest change to change from pcre to pcre2 #54

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
7f2ed38
Simplest change to change from pcre to pcre2
paulrho Nov 22, 2021
e71e724
Fix library reference for PCRE2
paulrho Nov 22, 2021
6c2110c
remove pcre2 ..-32, remove debug fprintf
paulrho Nov 22, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions Makefile.am
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,14 +13,14 @@ bti_CFLAGS = \
$(LIBCURL_CFLAGS) \
$(XML_CFLAGS) \
$(JSON_CFLAGS) \
$(LIBPCRE_CFLAGS) \
$(PCRE2_CFLAGS) \
$(LIBOAUTH_CFLAGS)

bti_LDADD = \
$(LIBCURL_LIBS) \
$(XML_LIBS) \
$(JSON_LIBS) \
$(LIBPCRE_LIBS) \
$(PCRE2_LIBS) \
$(LIBOAUTH_LIBS)

dist_man_MANS = \
Expand Down
33 changes: 23 additions & 10 deletions bti.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,9 @@

#define _GNU_SOURCE

#define is_error(ptr) (ptr == NULL)

#define PCRE2_CODE_UNIT_WIDTH 8
#include <stdio.h>
#include <stdlib.h>
#include <stddef.h>
Expand All @@ -33,7 +36,7 @@
#include <libxml/parser.h>
#include <libxml/tree.h>
#include <json-c/json.h>
#include <pcre.h>
#include <pcre2.h>
#include <termios.h>
#include <dlfcn.h>
#include <oauth.h>
Expand Down Expand Up @@ -1260,20 +1263,22 @@ static int find_urls(const char *tweet, int **pranges)
"(([a-zA-Z][0-9a-zA-Z+\\-\\.]*:)/{1,3}"
"[0-9a-zA-Z;/~?:@&=+$\\.\\-_'()%]+)"
"(#[0-9a-zA-Z;/?:@&=+$\\.\\-_!~*'()%]+)?";
pcre *re;
pcre2_code *re;
const char *errptr;
int errorcode;
int erroffset;
int ovector[10] = {0,};
//int ovector[10] = {0,};
PCRE2_SIZE *ovector;
const size_t ovsize = sizeof(ovector)/sizeof(*ovector);
int startoffset, tweetlen;
int i, rc;
int rbound = 10;
int rcount = 0;
int *ranges = malloc(sizeof(int) * rbound);

re = pcre_compile(re_magic,
PCRE_NO_AUTO_CAPTURE,
&errptr, &erroffset, NULL);
re = pcre2_compile((PCRE2_SPTR)re_magic, PCRE2_ZERO_TERMINATED,
PCRE2_NO_AUTO_CAPTURE,
&errorcode, (PCRE2_SIZE*) &erroffset, NULL);
if (!re) {
fprintf(stderr, "pcre_compile @%u: %s\n", erroffset, errptr);
exit(1);
Expand All @@ -1282,9 +1287,11 @@ static int find_urls(const char *tweet, int **pranges)
tweetlen = strlen(tweet);
for (startoffset = 0; startoffset < tweetlen; ) {

rc = pcre_exec(re, NULL, tweet, strlen(tweet), startoffset, 0,
ovector, ovsize);
if (rc == PCRE_ERROR_NOMATCH)
pcre2_match_data *match_data;
match_data = pcre2_match_data_create_from_pattern(re, NULL);

rc = pcre2_match(re, (PCRE2_SPTR)tweet, strlen(tweet), startoffset, 0, match_data, NULL);
if (rc == PCRE2_ERROR_NOMATCH)
break;

if (rc < 0) {
Expand All @@ -1293,6 +1300,9 @@ static int find_urls(const char *tweet, int **pranges)
exit(1);
}

ovector = pcre2_get_ovector_pointer(match_data);
fprintf(stderr,"Match succeeded at offset %d to %d\n", (int)ovector[0], (int)ovector[1]);

for (i = 0; i < rc; i += 2) {
if ((rcount+2) == rbound) {
rbound *= 2;
Expand All @@ -1306,7 +1316,10 @@ static int find_urls(const char *tweet, int **pranges)
startoffset = ovector[1];
}

pcre_free(re);
//pcre2_match_data_free(re);
pcre2_code_free(re);

for (int i=0; i<rcount; i+=2) fprintf(stderr,"RANGE %d from %d to %d\n",i,ranges[i],ranges[i+1]);

*pranges = ranges;
return rcount;
Expand Down
3 changes: 2 additions & 1 deletion config.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,7 @@

#define _GNU_SOURCE

#define PCRE2_CODE_UNIT_WIDTH 8
#include <stdio.h>
#include <stdlib.h>
#include <stddef.h>
Expand All @@ -32,7 +33,7 @@
#include <libxml/xmlmemory.h>
#include <libxml/parser.h>
#include <libxml/tree.h>
#include <pcre.h>
#include <pcre2.h>
#include <termios.h>
#include <dlfcn.h>
#include <oauth.h>
Expand Down
6 changes: 4 additions & 2 deletions configure.ac
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,8 @@
AC_INIT([bti], [034], [[email protected]])
AC_PREREQ(2.60)

AM_INIT_AUTOMAKE(bti, 034)
#AM_INIT_AUTOMAKE(bti, 034)
AM_INIT_AUTOMAKE

m4_ifdef([AM_SILENT_RULES], [AM_SILENT_RULES([yes])])

Expand All @@ -15,7 +16,8 @@ AC_PATH_PROG([XSLTPROC], [xsltproc])
PKG_PROG_PKG_CONFIG()

PKG_CHECK_MODULES(LIBOAUTH, oauth)
PKG_CHECK_MODULES(LIBPCRE, libpcre)
#PKG_CHECK_MODULES(LIBPCRE2, libpcre2)
PKG_CHECK_MODULES(PCRE2, [libpcre2-8 libpcre2-32])
Copy link
Copy Markdown
Contributor

@gregoa gregoa Nov 22, 2021

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Just curious: why -8 and -32?
On my Debian/unstable system I can see:

/usr/lib/x86_64-linux-gnu/pkgconfig/libpcre2-16.pc
/usr/lib/x86_64-linux-gnu/pkgconfig/libpcre2-32.pc
/usr/lib/x86_64-linux-gnu/pkgconfig/libpcre2-8.pc
/usr/lib/x86_64-linux-gnu/pkgconfig/libpcre2-posix.pc

Copy link
Copy Markdown
Contributor Author

@paulrho paulrho Nov 22, 2021

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I've removed the -32

PKG_CHECK_MODULES([LIBCURL], [libcurl])
PKG_CHECK_MODULES([XML], [libxml-2.0])
PKG_CHECK_MODULES([JSON], [json-c])
Expand Down