diff options
| author | Steve Bennett <steveb@workware.net.au> | 2019-10-27 21:17:42 +1000 |
|---|---|---|
| committer | Steve Bennett <steveb@workware.net.au> | 2019-10-27 21:17:42 +1000 |
| commit | 9eba9e87fc3ed257bf82c1bc7e2f77dba1aaf9a5 (patch) | |
| tree | a439f53d186ac7431935b91c4b52a8f7d38eb7dc /jim-regexp.c | |
| parent | 38c389a29e8ff582ba32c7737bb90f0f0df12078 (diff) | |
| download | jimtcl-9eba9e87fc3ed257bf82c1bc7e2f77dba1aaf9a5.zip jimtcl-9eba9e87fc3ed257bf82c1bc7e2f77dba1aaf9a5.tar.gz jimtcl-9eba9e87fc3ed257bf82c1bc7e2f77dba1aaf9a5.tar.bz2 | |
regexp -indices should return character indices
Not byte indices
Reported-by: dbohdan <dbohdan@dbohdan.com>
Signed-off-by: Steve Bennett <steveb@workware.net.au>
Diffstat (limited to 'jim-regexp.c')
| -rw-r--r-- | jim-regexp.c | 15 |
1 files changed, 7 insertions, 8 deletions
diff --git a/jim-regexp.c b/jim-regexp.c index 81f3207..3134598 100644 --- a/jim-regexp.c +++ b/jim-regexp.c @@ -281,16 +281,15 @@ int Jim_RegexpCmd(Jim_Interp *interp, int argc, Jim_Obj *const *argv) } } else { - int len = pmatch[j].rm_eo - pmatch[j].rm_so; - if (opt_indices) { - Jim_ListAppendElement(interp, resultObj, Jim_NewIntObj(interp, - offset + pmatch[j].rm_so)); - Jim_ListAppendElement(interp, resultObj, Jim_NewIntObj(interp, - offset + pmatch[j].rm_so + len - 1)); + /* rm_so and rm_eo are byte offsets. We need char offsets */ + int so = utf8_strlen(source_str, pmatch[j].rm_so); + int eo = utf8_strlen(source_str + pmatch[j].rm_so, pmatch[j].rm_eo); + Jim_ListAppendElement(interp, resultObj, Jim_NewIntObj(interp, offset + so)); + Jim_ListAppendElement(interp, resultObj, Jim_NewIntObj(interp, offset + eo - 1)); } else { - Jim_AppendString(interp, resultObj, source_str + pmatch[j].rm_so, len); + Jim_AppendString(interp, resultObj, source_str + pmatch[j].rm_so, pmatch[j].rm_eo - pmatch[j].rm_so); } } @@ -311,7 +310,7 @@ int Jim_RegexpCmd(Jim_Interp *interp, int argc, Jim_Obj *const *argv) try_next_match: if (opt_all && (pattern[0] != '^' || (regcomp_flags & REG_NEWLINE)) && *source_str) { if (pmatch[0].rm_eo) { - offset += pmatch[0].rm_eo; + offset += utf8_strlen(source_str, pmatch[0].rm_eo); source_str += pmatch[0].rm_eo; } else { |