This is an automated email from the git hooks/post-receive script. rene pushed a commit to branch master in repository hunspell.
commit a821573d97eeecf43ce708fa7842fce5b7e77911 Author: Rene Engelhard <[email protected]> Date: Thu Apr 21 14:45:16 2016 +0200 Imported Upstream version 1.1.9 --- ChangeLog | 48 ++++- NEWS | 11 ++ THANKS | 4 + TODO | 3 +- configure | 20 +- configure.ac | 4 +- man/hunspell.1 | 9 +- man/hunspell.4 | 18 +- src/hunspell/affixmgr.cxx | 1 + src/hunspell/hashmgr.cxx | 94 ++++----- src/hunspell/hashmgr.hxx | 2 + src/parsers/htmlparser.cxx | 6 +- src/parsers/latexparser.cxx | 6 +- src/parsers/manparser.cxx | 7 +- src/parsers/testparser.cxx | 1 + src/parsers/textparser.cxx | 96 +++++++++- src/parsers/textparser.hxx | 9 +- src/tools/hunspell.cxx | 7 + src/win_api/Hunspell.rc | 32 ++++ src/win_api/Hunspell.sln | 26 +++ src/win_api/Hunspell.vcproj | 458 ++++++++++++++++++++++++++++++++++++++++++++ src/win_api/Makefile.am | 3 +- src/win_api/Makefile.in | 4 +- src/win_api/config.h | 214 +++++++++++++++++++++ tests/1706659.aff | 13 ++ tests/1706659.dic | 4 + tests/1706659.test | 4 + tests/1706659.wrong | 3 + tests/Makefile.am | 18 +- tests/Makefile.in | 18 +- tests/colons_in_words.aff | 3 + tests/colons_in_words.dic | 4 + tests/colons_in_words.test | 4 + tests/digits_in_words.aff | 9 + tests/digits_in_words.dic | 12 ++ tests/digits_in_words.test | 4 + tests/digits_in_words.wrong | 1 + 37 files changed, 1086 insertions(+), 94 deletions(-) diff --git a/ChangeLog b/ChangeLog index ef72bb7..fb54adf 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,46 @@ -2007-07-16 Németh László <nemeth at OOo>: +2007-07-25 Németh László <nemeth at OOo>: + * parsers/*.cxx: Hunspell executable recognises and accepts URLs, + e-mail addresses, directory paths, reported by Jeppe Bundsgaard. + * src/tools/hunspell.cxx: --check-url: new option of Hunspell program. + Use --check-url, if you want check URLs, e-mail addresses and paths. + + * parsers/textparser.cxx: strip colon at end of words for Finnish + and Swedish (colon may be in words in Finnish and Swedish). + Problem reported by Lars Aronsson. + * tests/colons_in_words.*: test data + + * tests/digits_in_words.*: example for using digits in words + (eg. 1-jährig, 112-jährig etc. in German), reported by Lars Aronsson. + + * hashmgr.cxx: Hunspell accepts allcaps forms of mixed case + words of personal dictionaries (+allcaps custom dictionary words with + allcaps affixes). + Sf.net Bug ID 1755272, reported by Ellis Miller. + + * hashmgr.cxx: fix small memory leaks with alias compressed + dictionaries (free flag vectors of affixed personal dictionary words + and flag vectors of hidden capitalized forms of mixed case and + allcaps words). + + * affixmgr.cxx: fix COMPOUNDRULE checking with affixed compounds. + Sf.net Bug ID 1706659, reported by Björn Jacke. + + * tools/hunspell.cxx: add missing return to save_privdic(). + + * man/hunspell.4: add information about affixation of personal words: + "Personal dictionaries are simple word lists, but with optional + word patterns for affixation, separated by a slash: + + foo + Foo/Simpson + + In this example, "foo" and "Foo" are personal words, plus Foo + will be recognised with affixes of Simpson (Foo's etc.)." + +2007-07-18 Németh László <nemeth at OOo>: + * src/win_api/: add missing resource files, reported by Ingo H. De Boer. + +2007-07-16 Németh László <nemeth at OOo>: * hunspell.cxx: fix dot removing from UTF-8 encoded words in cleanword2() (Capitalised words with dots, as "Something." were not recognised using Unicode encoded dictionaries.) @@ -41,7 +83,7 @@ * {dictmgr,csutil,hashmgr,suggestmgr}.cxx: check memory allocation. Sf.net Bug ID 1747507, based on the patch by Jose da Silva. -2007-07-13 Ingo H. De Boer <idb_winshell at SF.net>: +2007-07-13 Ingo H. De Boer <idb_winshell at SF.net>: * atypes.cxx: fix Visual C compatibility: Using "HUNSPELL_WARNING(a,b,...} {}" macro instead of empty "X(a,b...)". @@ -51,7 +93,7 @@ Sf.net Bug ID 1753802, patch by Ingo H. de Boer. See also Sf.net Bug ID 1751406, patch by Mike Tian-Jian Jiang. -2007-07-09 Caolan McNamara <cmc at OO.o>: +2007-07-09 Caolan McNamara <cmc at OO.o>: * {hunspell,hashmgr,affentry}.cxx: fix warnings of Coverity program analyzer. Sf.net Bug ID, 1750219. diff --git a/NEWS b/NEWS index b5e12d0..2d84c73 100644 --- a/NEWS +++ b/NEWS @@ -1,3 +1,14 @@ +2007-07-25: Hunspell 1.1.9 release: + - better tokenization: + - for URLs, mail addresses and directory paths (default: skip these tokens) + - for colons in words (for Finnish and Swedish) + + - new examples: + - affixation of personal dictionary words + - digits in words + + - bug fixes (see ChangeLog) + 2007-07-16: Hunspell 1.1.8 release: - better Mac OS X/Cygwin and Windows compatibility diff --git a/THANKS b/THANKS index 02bb5e3..cbc4fc9 100644 --- a/THANKS +++ b/THANKS @@ -1,9 +1,11 @@ Many thanks to the following contributors and supporters: +Lars Aronsson Bencsáth Boldizsár Bíró Árpád Ingo H. de Boer Simon Brouwer +Jeppe Bundsgaard Dmitri Gabinski Dvornik László David Einstein @@ -34,6 +36,7 @@ Marot at SF dot net Caolan McNamara Michael Meeks Moheb Mekhaiel +Ellis Miller Giuseppe Modugno Bram Moolenaar Daniel Naber @@ -48,6 +51,7 @@ Erdal Ronahi Bernhard Rosenkraenzer Sarlós Tamás Thobias Schlemmer +Jose da Silva Munzir Taha Tímár András Tonal at OOo diff --git a/TODO b/TODO index 766a8e0..51d589c 100644 --- a/TODO +++ b/TODO @@ -1,9 +1,8 @@ +* sounds-alike suggestions * shared dictionaries for multi-user environment * new data structure for morphological analysis * implement morphological generation * improve compound handling * implement complete stemming -* check Unicode user interface (for Hunspell program) -* handle different encodings (for Hunspell program) * Unicode unmunch (munch) * forbiddenword and pseudoword support in unmunch diff --git a/configure b/configure index 0b3be98..eedcf51 100755 --- a/configure +++ b/configure @@ -1,6 +1,6 @@ #! /bin/sh # Guess values for system-dependent variables and create Makefiles. -# Generated by GNU Autoconf 2.59 for hunspell 1.1.8. +# Generated by GNU Autoconf 2.59 for hunspell 1.1.9. # # Report bugs to <[email protected]>. # @@ -423,8 +423,8 @@ SHELL=${CONFIG_SHELL-/bin/sh} # Identity of this package. PACKAGE_NAME='hunspell' PACKAGE_TARNAME='hunspell' -PACKAGE_VERSION='1.1.8' -PACKAGE_STRING='hunspell 1.1.8' +PACKAGE_VERSION='1.1.9' +PACKAGE_STRING='hunspell 1.1.9' PACKAGE_BUGREPORT='[email protected]' ac_unique_file="config.h.in" @@ -954,7 +954,7 @@ if test "$ac_init_help" = "long"; then # Omit some internal or obsolete options to make the list less imposing. # This message is too long to be a string in the A/UX 3.1 sh. cat <<_ACEOF -\`configure' configures hunspell 1.1.8 to adapt to many kinds of systems. +\`configure' configures hunspell 1.1.9 to adapt to many kinds of systems. Usage: $0 [OPTION]... [VAR=VALUE]... @@ -1021,7 +1021,7 @@ fi if test -n "$ac_init_help"; then case $ac_init_help in - short | recursive ) echo "Configuration of hunspell 1.1.8:";; + short | recursive ) echo "Configuration of hunspell 1.1.9:";; esac cat <<\_ACEOF @@ -1171,7 +1171,7 @@ fi test -n "$ac_init_help" && exit 0 if $ac_init_version; then cat <<\_ACEOF -hunspell configure 1.1.8 +hunspell configure 1.1.9 generated by GNU Autoconf 2.59 Copyright (C) 2003 Free Software Foundation, Inc. @@ -1185,7 +1185,7 @@ cat >&5 <<_ACEOF This file contains any messages produced by compilers while running configure, to aid debugging if configure makes a mistake. -It was created by hunspell $as_me 1.1.8, which was +It was created by hunspell $as_me 1.1.9, which was generated by GNU Autoconf 2.59. Invocation command line was $ $0 $@ @@ -1916,7 +1916,7 @@ fi # Define the identity of the package. PACKAGE=hunspell - VERSION=1.1.8 + VERSION=1.1.9 cat >>confdefs.h <<_ACEOF @@ -23886,7 +23886,7 @@ _ASBOX } >&5 cat >&5 <<_CSEOF -This file was extended by hunspell $as_me 1.1.8, which was +This file was extended by hunspell $as_me 1.1.9, which was generated by GNU Autoconf 2.59. Invocation command line was CONFIG_FILES = $CONFIG_FILES @@ -23949,7 +23949,7 @@ _ACEOF cat >>$CONFIG_STATUS <<_ACEOF ac_cs_version="\\ -hunspell config.status 1.1.8 +hunspell config.status 1.1.9 configured by $0, generated by GNU Autoconf 2.59, with options \\"`echo "$ac_configure_args" | sed 's/[\\""\`\$]/\\\\&/g'`\\" diff --git a/configure.ac b/configure.ac index 4e2e38c..53d1ac5 100644 --- a/configure.ac +++ b/configure.ac @@ -5,7 +5,7 @@ m4_pattern_allow AC_PREREQ(2.59) -AC_INIT([hunspell],[1.1.8],[[email protected]]) +AC_INIT([hunspell],[1.1.9],[[email protected]]) AC_CANONICAL_SYSTEM case "$host" in @@ -13,7 +13,7 @@ arm*) XFAILED="flagutf8.test maputf.test";; esac AC_SUBST(XFAILED) -AM_INIT_AUTOMAKE(hunspell, 1.1.8) +AM_INIT_AUTOMAKE(hunspell, 1.1.9) HUNSPELL_VERSION_MAJOR=`echo $VERSION | cut -d"." -f1` HUNSPELL_VERSION_MINOR=`echo $VERSION | cut -d"." -f2` AC_SUBST(HUNSPELL_VERSION_MAJOR) diff --git a/man/hunspell.1 b/man/hunspell.1 index 5e2e882..1ec76ca 100644 --- a/man/hunspell.1 +++ b/man/hunspell.1 @@ -261,6 +261,9 @@ in output lines beginning with '*', '+', and '\-', which simplifies interaction for some programs. .TP +.B \--check-url +Check URLs, e-mail addresses and directory paths. +.TP .B \-d " dic" Path of affix and dic files, without file extension. .TP @@ -269,14 +272,14 @@ Path of affix and dic files, without file extension. .B \-h, \-\-help Short help. .TP -.B \-p " custom_dictionary" -Set path of custom dictionary. +.B \-p " personal_dictionary" +Set path of personal dictionary. Default is $HOME/.hunspell_default. Setting .I \-d or the .I DICTIONARY -environmental variable, custom dictionary will be +environmental variable, personal dictionary will be .BR $HOME/.hunspell_dicname .TP .B \-u diff --git a/man/hunspell.4 b/man/hunspell.4 index 472879e..ef25d5f 100644 --- a/man/hunspell.4 +++ b/man/hunspell.4 @@ -22,6 +22,21 @@ by tabulator. Morphological desciptions have custom format. +Personal dictionaries are simple word lists, but with optional +word patterns for affixation, separated by a slash: + +.PP +.RS +.nf +foo +Foo/Simpson +.fi +.RE +.PP + +In this example, "foo" and "Foo" are personal words, plus Foo +will be recognised with affixes of Simpson (Foo's etc.). + An affix file (*.aff) may contain a lot of optional attributes. For example, .B SET @@ -1020,9 +1035,6 @@ D condition characters, and sorted UTF-16 lists for other Unicode characters of condition patterns. -Hunspell has supported only the first 65536 characters (Basic Multilingual Plane) -of Unicode Standard, yet. - .SH "SEE ALSO" .B hunspell (1), .B ispell (1), diff --git a/src/hunspell/affixmgr.cxx b/src/hunspell/affixmgr.cxx index 033c6e7..d114924 100644 --- a/src/hunspell/affixmgr.cxx +++ b/src/hunspell/affixmgr.cxx @@ -1768,6 +1768,7 @@ struct hentry * AffixMgr::compound_check(const char * word, int len, if (!rv && numdefcpd && words) { rv = affix_check((word+i),strlen(word+i), 0, IN_CPD_END); if (rv && defcpd_check(&words, wnum + 1, rv, NULL, 1)) return rv; + rv = NULL; } // check non_compound flag in suffix and prefix diff --git a/src/hunspell/hashmgr.cxx b/src/hunspell/hashmgr.cxx index 90bb5f7..1a137b1 100644 --- a/src/hunspell/hashmgr.cxx +++ b/src/hunspell/hashmgr.cxx @@ -70,7 +70,7 @@ HashMgr::~HashMgr() struct hentry * pt = &tableptr[i]; struct hentry * nt = NULL; if (pt) { - if (pt->astr && !aliasf) free(pt->astr); + if (pt->astr && (!aliasf || TESTAFF(pt->astr, ONLYUPCASEFLAG, pt->alen))) free(pt->astr); if (pt->word) free(pt->word); #ifdef HUNSPELL_EXPERIMENTAL if (pt->description && !aliasm) free(pt->description); @@ -79,7 +79,7 @@ HashMgr::~HashMgr() } while(pt) { nt = pt->next; - if (pt->astr && !aliasf) free(pt->astr); + if (pt->astr && (!aliasf || TESTAFF(pt->astr, ONLYUPCASEFLAG, pt->alen))) free(pt->astr); if (pt->word) free(pt->word); #ifdef HUNSPELL_EXPERIMENTAL if (pt->description && !aliasm) free(pt->description); @@ -256,6 +256,37 @@ desc return 0; } +int HashMgr::add_hidden_capitalized_word(char * word, int wl, + unsigned short * flags, int al, char * dp) +{ + // add inner capitalized forms to handle the following allcap forms: + // Mixed caps: OpenOffice.org -> OPENOFFICE.ORG + // Allcaps with suffixes: CIA's -> CIA'S + int captype = utf8 ? get_captype_utf8(word, wl, langnum) : get_captype(word, wl, csconv); + if (((captype == HUHCAP) || (captype == HUHINITCAP) || + ((captype == ALLCAP) && (flags != NULL))) && + !((flags != NULL) && TESTAFF(flags, forbiddenword, al))) { + unsigned short * flags2 = (unsigned short *) malloc (sizeof(unsigned short) * (al+1)); + if (!flags2) return 1; + if (al) memcpy(flags2, flags, al * sizeof(unsigned short)); + flags2[al] = ONLYUPCASEFLAG; + if (utf8) { + char st[MAXDELEN]; + w_char w[MAXDELEN]; + int wlen = u8_u16(w, MAXDELEN, word); + mkallsmall_utf(w, wlen, langnum); + mkallcap_utf(w, 1, langnum); + u16_u8(st, MAXDELEN, w, wlen); + return add_word(st,wl,flags2,al+1,dp, true); + } else { + mkallsmall(word, csconv); + mkinitcap(word, csconv); + return add_word(word,wl,flags2,al+1,dp, true); + } + } + return 0; +} + // add a custom dic. word to the hash table (public) int HashMgr::put_word(const char * word, int wl, char * aff) { @@ -268,19 +299,23 @@ int HashMgr::put_word(const char * word, int wl, char * aff) flags = NULL; } add_word(word, wl, flags, al, NULL, false); - return 0; + return add_hidden_capitalized_word((char *) word, wl, flags, al, NULL); } int HashMgr::put_word_pattern(const char * word, int wl, const char * pattern) { - unsigned short * flags; struct hentry * dp = lookup(pattern); - if (!dp || !dp->astr) return 1; - flags = (unsigned short *) malloc (dp->alen * sizeof(short)); - if (flags) { - memcpy((void *) flags, (void *) dp->astr, dp->alen * sizeof(short)); - add_word(word, wl, flags, dp->alen, NULL, false); - return 0; + if (dp && dp->astr) { + if (aliasf) { + add_word(word, wl, dp->astr, dp->alen, NULL, false); + } else { + unsigned short * flags = (unsigned short *) malloc (dp->alen * sizeof(short)); + if (flags) { + memcpy((void *) flags, (void *) dp->astr, dp->alen * sizeof(short)); + add_word(word, wl, flags, dp->alen, NULL, false); + } else return 1; + } + return add_hidden_capitalized_word((char *) word, wl, dp->astr, dp->alen, NULL); } return 1; } @@ -318,7 +353,6 @@ int HashMgr::load_tables(const char * tpath) char * ap; char * dp; unsigned short * flags; - int captype; // raw dictionary - munched file FILE * rawdict = fopen(tpath, "r"); @@ -405,44 +439,12 @@ int HashMgr::load_tables(const char * tpath) } wl = strlen(ts); - - // add the word and its index - if (add_word(ts,wl,flags,al,dp, false)) { + // add the word and its index plus its capitalized form optionally + if (add_word(ts,wl,flags,al,dp, false) || + add_hidden_capitalized_word(ts, wl, flags, al, dp)) { fclose(rawdict); return 5; } - - // add inner capitalized forms to handle the following allcap forms: - // Mixed caps: OpenOffice.org -> OPENOFFICE.ORG - // Allcaps with suffixes: CIA's -> CIA'S - captype = utf8 ? get_captype_utf8(ts, wl, langnum) : get_captype(ts, wl, csconv); - if (((captype == HUHCAP) || (captype == HUHINITCAP) || - ((captype == ALLCAP) && (flags != NULL))) && - !((flags != NULL) && TESTAFF(flags, forbiddenword, al))) { - unsigned short * flags2 = (unsigned short *) malloc (sizeof(unsigned short) * (al+1)); - if (!flags2) return 6; - if (al) memcpy(flags2, flags, al * sizeof(unsigned short)); - flags2[al] = ONLYUPCASEFLAG; - if (utf8) { - char st[MAXDELEN]; - w_char w[MAXDELEN]; - int wlen = u8_u16(w, MAXDELEN, ts); - mkallsmall_utf(w, wlen, langnum); - mkallcap_utf(w, 1, langnum); - u16_u8(st, MAXDELEN, w, wlen); - if (add_word(st,wl,flags2,al+1,dp, true)) { - fclose(rawdict); - return 5; - } - } else { - mkallsmall(ts, csconv); - mkinitcap(ts, csconv); - if (add_word(ts,wl,flags2,al+1,dp, true)) { - fclose(rawdict); - return 5; - } - } - } } fclose(rawdict); diff --git a/src/hunspell/hashmgr.hxx b/src/hunspell/hashmgr.hxx index b33b026..6b9641e 100644 --- a/src/hunspell/hashmgr.hxx +++ b/src/hunspell/hashmgr.hxx @@ -56,6 +56,8 @@ private: const char * desc, bool onlyupcase); int load_config(const char * affpath); int parse_aliasf(char * line, FILE * af); + int add_hidden_capitalized_word(char * word, int wl, + unsigned short * flags, int al, char * dp); #ifdef HUNSPELL_EXPERIMENTAL int parse_aliasm(char * line, FILE * af); #endif diff --git a/src/parsers/htmlparser.cxx b/src/parsers/htmlparser.cxx index c475466..06ead69 100644 --- a/src/parsers/htmlparser.cxx +++ b/src/parsers/htmlparser.cxx @@ -106,10 +106,8 @@ char * HTMLParser::next_token() head += strlen(latin1); } else if (! is_wordchar(line[actual] + head)) { state = prevstate; - char * t = (char *) malloc(head - token + 1); - t[head - token] = '\0'; - if (t) return strncpy(t, line[actual] + token, head - token); - fprintf(stderr,"Error - Insufficient Memory\n"); + char * t = alloc_token(token, &head); + if (t) return t; } break; case ST_TAG: // comment, labels, etc diff --git a/src/parsers/latexparser.cxx b/src/parsers/latexparser.cxx index eecbede..4b0a326 100644 --- a/src/parsers/latexparser.cxx +++ b/src/parsers/latexparser.cxx @@ -166,10 +166,8 @@ char * LaTeXParser::next_token() case 1: // wordchar if (! is_wordchar(line[actual] + head)) { state = 0; - char * t = (char *) malloc(head - token + 1); - t[head - token] = '\0'; - if (t) return strncpy(t, line[actual] + token, head - token); - fprintf(stderr,"Error - Insufficient Memory\n"); + char * t = alloc_token(token, &head); + if (t) return t; } break; case 2: // comment, labels, etc diff --git a/src/parsers/manparser.cxx b/src/parsers/manparser.cxx index 1261a86..25858da 100644 --- a/src/parsers/manparser.cxx +++ b/src/parsers/manparser.cxx @@ -17,7 +17,6 @@ ManParser::ManParser() { ManParser::ManParser(const char * wordchars) { init(wordchars); - // wordcharacters[('/' + 256) % 256] = 1; // for paths } ManParser::ManParser(unsigned short * wordchars, int len) @@ -58,10 +57,8 @@ char * ManParser::next_token() case 3: // wordchar if (! is_wordchar(line[actual] + head)) { state = 2; - char * t = (char *) malloc(head - token + 1); - t[head - token] = '\0'; - if (t) return strncpy(t, line[actual] + token, head - token); - fprintf(stderr,"Error - Insufficient Memory\n"); + char * t = alloc_token(token, &head); + if (t) return t; } break; } diff --git a/src/parsers/testparser.cxx b/src/parsers/testparser.cxx index c0cb913..7a394cd 100644 --- a/src/parsers/testparser.cxx +++ b/src/parsers/testparser.cxx @@ -38,6 +38,7 @@ main(int argc, char** argv) while(fgets(buf,MAXLNLEN,f)) { fprintf(stdout,"---------------------------------------\n"); p->put_line(buf); + p->set_url_checking(1); while ((next=p->next_token())) { fprintf(stdout,"token: %s\n",next); free(next); diff --git a/src/parsers/textparser.cxx b/src/parsers/textparser.cxx index 97037b4..b691262 100644 --- a/src/parsers/textparser.cxx +++ b/src/parsers/textparser.cxx @@ -99,9 +99,11 @@ void TextParser::init(const char * wordchars) token = 0; state = 0; utf8 = 0; + checkurl = 0; unsigned int j; - for (j = 0; j < 256; j++) + for (j = 0; j < 256; j++) { wordcharacters[j] = 0; + } if (!wordchars) wordchars = "qwertzuiopasdfghjklyxcvbnmQWERTZUIOPASDFGHJKLYXCVBNM"; for (j = 0; j < strlen(wordchars); j++) { wordcharacters[(wordchars[j] + 256) % 256] = 1; @@ -118,6 +120,7 @@ void TextParser::init(unsigned short * wc, int len) token = 0; state = 0; utf8 = 1; + checkurl = 0; wordchars_utf16 = wc; wclen = len; } @@ -141,6 +144,7 @@ void TextParser::put_line(char * word) strcpy(line[actual], word); token = 0; head = 0; + check_urls(); } char * TextParser::get_prevline(int n) @@ -175,10 +179,8 @@ char * TextParser::next_token() head += strlen(latin1); } else if (! is_wordchar(line[actual] + head)) { state = 0; - char * t = (char *) malloc(head - token + 1); - t[head - token] = '\0'; - if (t) return strncpy(t, line[actual] + token, head - token); - fprintf(stderr,"Error - Insufficient Memory\n"); + char * t = alloc_token(token, &head); + if (t) return t; } break; } @@ -203,3 +205,87 @@ int TextParser::change_token(const char * word) } return 0; } + +void TextParser::check_urls() +{ + int url_state = 0; + int url_head = 0; + int url_token = 0; + int url = 0; + for (;;) { + switch (url_state) + { + case 0: // non word chars + if (is_wordchar(line[actual] + url_head)) { + url_state = 1; + url_token = url_head; + // Unix path + } else if (*(line[actual] + url_head) == '/') { + url_state = 1; + url_token = url_head; + url = 1; + } + break; + case 1: // wordchar + char ch = *(line[actual] + url_head); + // e-mail address + if ((ch == '@') || + // MS-DOS, Windows path + (strncmp(line[actual] + url_head, ":\\", 2) == 0) || + // URL + (strncmp(line[actual] + url_head, "://", 3) == 0)) { + url = 1; + } else if (! (is_wordchar(line[actual] + url_head) || + (ch == '-') || (ch == '_') || (ch == '\\') || + (ch == '.') || (ch == ':') || (ch == '/') || + (ch == '~') || (ch == '%') || (ch == '*') || + (ch == '$') || (ch == '[') || (ch == ']') || + (ch == '?') || (ch == '!') || + ((ch >= '0') && (ch <= '9')))) { + url_state = 0; + if (url == 1) { + for (int i = url_token; i < url_head; i++) { + *(urlline + i) = 1; + } + } + url = 0; + } + break; + } + *(urlline + url_head) = 0; + if (next_char(line[actual], &url_head)) return; + } +} + +int TextParser::get_url(int token_pos, int * head) +{ + for (int i = *head; urlline[i] && *(line[actual]+i); i++, (*head)++); + return checkurl ? 0 : urlline[token_pos]; +} + +void TextParser::set_url_checking(int check) +{ + checkurl = check; +} + + +char * TextParser::alloc_token(int token, int * head) +{ + if (get_url(token, head)) return NULL; + char * t = (char *) malloc(*head - token + 1); + if (t) { + t[*head - token] = '\0'; + strncpy(t, line[actual] + token, *head - token); + // remove colon for Finnish and Swedish language + if (t[*head - token - 1] == ':') { + t[*head - token - 1] = '\0'; + if (!t[0]) { + free(t); + return NULL; + } + } + return t; + } + fprintf(stderr,"Error - Insufficient Memory\n"); + return NULL; +} diff --git a/src/parsers/textparser.hxx b/src/parsers/textparser.hxx index 1049d86..5bf1894 100644 --- a/src/parsers/textparser.hxx +++ b/src/parsers/textparser.hxx @@ -28,6 +28,8 @@ protected: void init(unsigned short * wordchars, int len); int wordcharacters[256]; // for detection of the word boundaries char line[MAXPREVLINE][MAXLNLEN]; // parsed and previous lines + char urlline[MAXLNLEN]; // mask for url detection + int checkurl; int actual; // actual line int head; // head position int token; // begin of token @@ -49,11 +51,16 @@ public: char * get_prevline(int n); virtual char * next_token(); int change_token(const char * word); + void set_url_checking(int check); + int get_tokenpos(); int is_wordchar(char * w); char * get_latin1(char * s); char * next_char(); - + int tokenize_urls(); + void check_urls(); + int get_url(int token_pos, int * head); + char * alloc_token(int token, int * head); }; #endif diff --git a/src/tools/hunspell.cxx b/src/tools/hunspell.cxx index be1f3f9..1fba8d6 100644 --- a/src/tools/hunspell.cxx +++ b/src/tools/hunspell.cxx @@ -150,6 +150,7 @@ enum { NORMAL, int filter_mode = NORMAL; int printgood = 0; // print only good words and lines int showpath = 0; // show detected path of the dictionary +int checkurl = 0; // check URLs and mail addresses char * ui_lang = NULL; // locale for default dic_name const char * ui_enc = NULL; // locale character encoding (default for I/O) const char * io_enc = NULL; // I/O character encoding @@ -328,6 +329,7 @@ TextParser * get_parser(int format, char * extension, Hunspell * pMS) { p = new TextParser(wordchars); } } + p->set_url_checking(checkurl); return p; } @@ -411,6 +413,7 @@ int save_privdic(char * filename, char * filename2, wordlist * w) free(r); } fclose(dic); + return 1; } char * basename(char * s, char c) { @@ -473,6 +476,7 @@ nextline: while(fgets(buf, MAXLNLEN, fileid)) { case '+': { delete parser; parser = new LaTeXParser(wordchars); + parser->set_url_checking(checkurl); break; } case '-': { @@ -1261,6 +1265,7 @@ int main(int argc, char** argv) fprintf(stderr,"\n"); fprintf(stderr,gettext(" -1\t\tcheck only first field in lines (delimiter = tabulator)\n")); fprintf(stderr,gettext(" -a\t\tIspell's pipe interface\n")); + fprintf(stderr,gettext(" --check-url\tCheck URLs, e-mail addresses and directory paths\n")); fprintf(stderr,gettext(" -d dict\tuse dict dictionary\n")); fprintf(stderr,gettext(" -D\t\tshow detected path of the dictionary\n")); fprintf(stderr,gettext(" -G\t\tprint only correct words or lines\n")); @@ -1327,6 +1332,8 @@ int main(int argc, char** argv) format = FMT_FIRST; } else if ((strcmp(argv[i],"-D")==0)) { showpath = 1; + } else if ((strcmp(argv[i],"--check-url")==0)) { + checkurl = 1; } else if ((arg_files==-1) && ((argv[i][0] != '-') && (argv[i][0] != '\0'))) { arg_files = i; if (! exist(argv[i])) { // first check (before time-consuming dic. load) diff --git a/src/win_api/Hunspell.rc b/src/win_api/Hunspell.rc new file mode 100644 index 0000000..bf57fd5 --- /dev/null +++ b/src/win_api/Hunspell.rc @@ -0,0 +1,32 @@ + +#include <windows.h> + +VS_VERSION_INFO VERSIONINFO +FILEVERSION 1,1,8,0 +PRODUCTVERSION 1,1,8,0 +FILEFLAGSMASK 0x17L +FILEFLAGS 0 +FILEOS VOS_NT_WINDOWS32 +FILETYPE VFT_APP +FILESUBTYPE VFT2_UNKNOWN +BEGIN + BLOCK "VarFileInfo" + BEGIN + VALUE "Translation", 0x409, 1200 + END + BLOCK "StringFileInfo" + BEGIN + BLOCK "040904b0" + BEGIN + VALUE "Comments", "Hunspell (http://hunspell.sourceforge.net/) by L�szl� N�meth" + VALUE "CompanyName", "http://hunspell.sourceforge.net/"; + VALUE "FileDescription", "Hunspell" + VALUE "FileVersion", "1.1.8" + VALUE "InternalName", "Hunspell" + VALUE "LegalCopyright", "Copyright (c) 2007" + VALUE "OriginalFilename", "Hunspell.dll" + VALUE "ProductName", "Hunspell Dynamic Link Library" + VALUE "ProductVersion", "1.1.8" + END + END +END diff --git a/src/win_api/Hunspell.sln b/src/win_api/Hunspell.sln new file mode 100644 index 0000000..c89282b --- /dev/null +++ b/src/win_api/Hunspell.sln @@ -0,0 +1,26 @@ + +Microsoft Visual Studio Solution File, Format Version 9.00 +# Visual Studio 2005 +Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "Hunspell", "Hunspell.vcproj", "{53609BB3-D874-465C-AF7B-DF626DB0D89B}" +EndProject +Global + GlobalSection(SolutionConfigurationPlatforms) = preSolution + Debug_dll|Win32 = Debug_dll|Win32 + Debug|Win32 = Debug|Win32 + Release_dll|Win32 = Release_dll|Win32 + Release|Win32 = Release|Win32 + EndGlobalSection + GlobalSection(ProjectConfigurationPlatforms) = postSolution + {53609BB3-D874-465C-AF7B-DF626DB0D89B}.Debug_dll|Win32.ActiveCfg = Debug_dll|Win32 + {53609BB3-D874-465C-AF7B-DF626DB0D89B}.Debug_dll|Win32.Build.0 = Debug_dll|Win32 + {53609BB3-D874-465C-AF7B-DF626DB0D89B}.Debug|Win32.ActiveCfg = Debug|Win32 + {53609BB3-D874-465C-AF7B-DF626DB0D89B}.Debug|Win32.Build.0 = Debug|Win32 + {53609BB3-D874-465C-AF7B-DF626DB0D89B}.Release_dll|Win32.ActiveCfg = Release_dll|Win32 + {53609BB3-D874-465C-AF7B-DF626DB0D89B}.Release_dll|Win32.Build.0 = Release_dll|Win32 + {53609BB3-D874-465C-AF7B-DF626DB0D89B}.Release|Win32.ActiveCfg = Release|Win32 + {53609BB3-D874-465C-AF7B-DF626DB0D89B}.Release|Win32.Build.0 = Release|Win32 + EndGlobalSection + GlobalSection(SolutionProperties) = preSolution + HideSolutionNode = FALSE + EndGlobalSection +EndGlobal diff --git a/src/win_api/Hunspell.vcproj b/src/win_api/Hunspell.vcproj new file mode 100644 index 0000000..a01ea47 --- /dev/null +++ b/src/win_api/Hunspell.vcproj @@ -0,0 +1,458 @@ +<?xml version="1.0" encoding="Windows-1252"?> +<VisualStudioProject + ProjectType="Visual C++" + Version="8,00" + Name="Hunspell" + ProjectGUID="{53609BB3-D874-465C-AF7B-DF626DB0D89B}" + RootNamespace="Hunspell" + Keyword="Win32Proj" + > + <Platforms> + <Platform + Name="Win32" + /> + </Platforms> + <ToolFiles> + </ToolFiles> + <Configurations> + <Configuration + Name="Debug|Win32" + OutputDirectory="$(SolutionDir)$(ConfigurationName)" + IntermediateDirectory="$(ConfigurationName)" + ConfigurationType="4" + UseOfMFC="0" + ATLMinimizesCRunTimeLibraryUsage="false" + CharacterSet="2" + > + <Tool + Name="VCPreBuildEventTool" + /> + <Tool + Name="VCCustomBuildTool" + /> + <Tool + Name="VCXMLDataGeneratorTool" + /> + <Tool + Name="VCWebServiceProxyGeneratorTool" + /> + <Tool + Name="VCMIDLTool" + /> + <Tool + Name="VCCLCompilerTool" + Optimization="0" + AdditionalIncludeDirectories="..\hunspell;." + PreprocessorDefinitions="WIN32;_DEBUG;_WINDOWS;_USRDLL;HUNSPELL_STATIC;_CRT_SECURE_NO_WARNINGS" + MinimalRebuild="false" + BasicRuntimeChecks="3" + RuntimeLibrary="3" + UsePrecompiledHeader="0" + WarningLevel="4" + Detect64BitPortabilityProblems="false" + DebugInformationFormat="4" + /> + <Tool + Name="VCManagedResourceCompilerTool" + /> + <Tool + Name="VCResourceCompilerTool" + /> + <Tool + Name="VCPreLinkEventTool" + /> + <Tool + Name="VCLibrarianTool" + /> + <Tool + Name="VCALinkTool" + /> + <Tool + Name="VCXDCMakeTool" + /> + <Tool + Name="VCBscMakeTool" + /> + <Tool + Name="VCFxCopTool" + /> + <Tool + Name="VCPostBuildEventTool" + /> + </Configuration> + <Configuration + Name="Release|Win32" + OutputDirectory="$(SolutionDir)$(ConfigurationName)" + IntermediateDirectory="$(ConfigurationName)" + ConfigurationType="4" + UseOfMFC="0" + ATLMinimizesCRunTimeLibraryUsage="false" + CharacterSet="2" + WholeProgramOptimization="1" + > + <Tool + Name="VCPreBuildEventTool" + /> + <Tool + Name="VCCustomBuildTool" + /> + <Tool + Name="VCXMLDataGeneratorTool" + /> + <Tool + Name="VCWebServiceProxyGeneratorTool" + /> + <Tool + Name="VCMIDLTool" + /> + <Tool + Name="VCCLCompilerTool" + Optimization="3" + InlineFunctionExpansion="2" + AdditionalIncludeDirectories="..\hunspell;." + PreprocessorDefinitions="WIN32;NDEBUG;_WINDOWS;_USRDLL;HUNSPELL_STATIC;_CRT_SECURE_NO_WARNINGS" + StringPooling="true" + RuntimeLibrary="0" + EnableFunctionLevelLinking="true" + UsePrecompiledHeader="0" + WarningLevel="4" + Detect64BitPortabilityProblems="false" + DebugInformationFormat="0" + /> + <Tool + Name="VCManagedResourceCompilerTool" + /> + <Tool + Name="VCResourceCompilerTool" + PreprocessorDefinitions="NDEBUG" + Culture="1033" + /> + <Tool + Name="VCPreLinkEventTool" + /> + <Tool + Name="VCLibrarianTool" + /> + <Tool + Name="VCALinkTool" + /> + <Tool + Name="VCXDCMakeTool" + /> + <Tool + Name="VCBscMakeTool" + SuppressStartupBanner="false" + /> + <Tool + Name="VCFxCopTool" + /> + <Tool + Name="VCPostBuildEventTool" + /> + </Configuration> + <Configuration + Name="Release_dll|Win32" + OutputDirectory="$(SolutionDir)$(ConfigurationName)" + IntermediateDirectory="$(ConfigurationName)" + ConfigurationType="2" + UseOfMFC="0" + ATLMinimizesCRunTimeLibraryUsage="false" + CharacterSet="2" + WholeProgramOptimization="1" + > + <Tool + Name="VCPreBuildEventTool" + /> + <Tool + Name="VCCustomBuildTool" + /> + <Tool + Name="VCXMLDataGeneratorTool" + /> + <Tool + Name="VCWebServiceProxyGeneratorTool" + /> + <Tool + Name="VCMIDLTool" + /> + <Tool + Name="VCCLCompilerTool" + Optimization="3" + InlineFunctionExpansion="2" + AdditionalIncludeDirectories="..\hunspell;." + PreprocessorDefinitions="WIN32;NDEBUG;_WINDOWS;_USRDLL;HUNSPELL_EXPORTS;_CRT_SECURE_NO_DEPRECATE" + StringPooling="true" + RuntimeLibrary="0" + EnableFunctionLevelLinking="true" + UsePrecompiledHeader="0" + WarningLevel="4" + Detect64BitPortabilityProblems="false" + DebugInformationFormat="0" + /> + <Tool + Name="VCManagedResourceCompilerTool" + /> + <Tool + Name="VCResourceCompilerTool" + PreprocessorDefinitions="NDEBUG" + Culture="1033" + /> + <Tool + Name="VCPreLinkEventTool" + /> + <Tool + Name="VCLinkerTool" + LinkIncremental="0" + GenerateDebugInformation="false" + SubSystem="2" + OptimizeReferences="2" + EnableCOMDATFolding="2" + TargetMachine="0" + /> + <Tool + Name="VCALinkTool" + /> + <Tool + Name="VCManifestTool" + /> + <Tool + Name="VCXDCMakeTool" + /> + <Tool + Name="VCBscMakeTool" + /> + <Tool + Name="VCFxCopTool" + /> + <Tool + Name="VCAppVerifierTool" + /> + <Tool + Name="VCWebDeploymentTool" + /> + <Tool + Name="VCPostBuildEventTool" + /> + </Configuration> + <Configuration + Name="Debug_dll|Win32" + OutputDirectory="$(SolutionDir)$(ConfigurationName)" + IntermediateDirectory="$(ConfigurationName)" + ConfigurationType="2" + UseOfMFC="0" + ATLMinimizesCRunTimeLibraryUsage="false" + CharacterSet="2" + > + <Tool + Name="VCPreBuildEventTool" + /> + <Tool + Name="VCCustomBuildTool" + /> + <Tool + Name="VCXMLDataGeneratorTool" + /> + <Tool + Name="VCWebServiceProxyGeneratorTool" + /> + <Tool + Name="VCMIDLTool" + /> + <Tool + Name="VCCLCompilerTool" + Optimization="0" + AdditionalIncludeDirectories="..\hunspell;." + PreprocessorDefinitions="WIN32;_DEBUG;_WINDOWS;_USRDLL;_CRT_SECURE_NO_WARNINGS;HUNSPELL_EXPORTS" + MinimalRebuild="false" + BasicRuntimeChecks="3" + RuntimeLibrary="3" + UsePrecompiledHeader="0" + WarningLevel="4" + Detect64BitPortabilityProblems="false" + DebugInformationFormat="4" + /> + <Tool + Name="VCManagedResourceCompilerTool" + /> + <Tool + Name="VCResourceCompilerTool" + /> + <Tool + Name="VCPreLinkEventTool" + /> + <Tool + Name="VCLinkerTool" + LinkIncremental="2" + GenerateDebugInformation="true" + SubSystem="2" + TargetMachine="1" + /> + <Tool + Name="VCALinkTool" + /> + <Tool + Name="VCManifestTool" + /> + <Tool + Name="VCXDCMakeTool" + /> + <Tool + Name="VCBscMakeTool" + /> + <Tool + Name="VCFxCopTool" + /> + <Tool + Name="VCAppVerifierTool" + /> + <Tool + Name="VCWebDeploymentTool" + /> + <Tool + Name="VCPostBuildEventTool" + /> + </Configuration> + </Configurations> + <References> + </References> + <Files> + <Filter + Name="_Main" + > + <File + RelativePath=".\config.h" + > + </File> + <File + RelativePath=".\Hunspell.rc" + > + </File> + <File + RelativePath=".\hunspelldll.c" + > + <FileConfiguration + Name="Debug|Win32" + > + <Tool + Name="VCCLCompilerTool" + CompileAs="2" + /> + </FileConfiguration> + <FileConfiguration + Name="Release|Win32" + > + <Tool + Name="VCCLCompilerTool" + CompileAs="2" + /> + </FileConfiguration> + <FileConfiguration + Name="Release_dll|Win32" + > + <Tool + Name="VCCLCompilerTool" + CompileAs="2" + /> + </FileConfiguration> + <FileConfiguration + Name="Debug_dll|Win32" + > + <Tool + Name="VCCLCompilerTool" + CompileAs="2" + /> + </FileConfiguration> + </File> + <File + RelativePath=".\hunspelldll.h" + > + </File> + </Filter> + <Filter + Name="hunspell" + > + <File + RelativePath="..\hunspell\affentry.cxx" + > + </File> + <File + RelativePath="..\hunspell\affentry.hxx" + > + </File> + <File + RelativePath="..\hunspell\affixmgr.cxx" + > + </File> + <File + RelativePath="..\hunspell\affixmgr.hxx" + > + </File> + <File + RelativePath="..\hunspell\atypes.hxx" + > + </File> + <File + RelativePath="..\hunspell\baseaffix.hxx" + > + </File> + <File + RelativePath="..\hunspell\csutil.cxx" + > + </File> + <File + RelativePath="..\hunspell\csutil.hxx" + > + </File> + <File + RelativePath="..\hunspell\dictmgr.cxx" + > + </File> + <File + RelativePath="..\hunspell\dictmgr.hxx" + > + </File> + <File + RelativePath="..\hunspell\hashmgr.cxx" + > + </File> + <File + RelativePath="..\hunspell\hashmgr.hxx" + > + </File> + <File + RelativePath="..\hunspell\htypes.hxx" + > + </File> + <File + RelativePath="..\hunspell\hunspell.cxx" + > + </File> + <File + RelativePath="..\hunspell\hunspell.h" + > + </File> + <File + RelativePath="..\hunspell\hunspell.hxx" + > + </File> + <File + RelativePath="..\hunspell\langnum.hxx" + > + </File> + <File + RelativePath="..\hunspell\suggestmgr.cxx" + > + </File> + <File + RelativePath="..\hunspell\suggestmgr.hxx" + > + </File> + <File + RelativePath="..\hunspell\utf_info.cxx" + > + </File> + </Filter> + </Files> + <Globals> + </Globals> +</VisualStudioProject> diff --git a/src/win_api/Makefile.am b/src/win_api/Makefile.am index b55a4ad..0d1f5fa 100644 --- a/src/win_api/Makefile.am +++ b/src/win_api/Makefile.am @@ -1 +1,2 @@ -EXTRA_DIST=hunspelldll.h hunspelldll.c hunspelldll.dev README +EXTRA_DIST=hunspelldll.h hunspelldll.c hunspelldll.dev README \ + config.h Hunspell.rc Hunspell.sln Hunspell.vcproj diff --git a/src/win_api/Makefile.in b/src/win_api/Makefile.in index b2712a1..e5e6980 100644 --- a/src/win_api/Makefile.in +++ b/src/win_api/Makefile.in @@ -183,7 +183,9 @@ target_alias = @target_alias@ target_cpu = @target_cpu@ target_os = @target_os@ target_vendor = @target_vendor@ -EXTRA_DIST = hunspelldll.h hunspelldll.c hunspelldll.dev README +EXTRA_DIST = hunspelldll.h hunspelldll.c hunspelldll.dev README \ + config.h Hunspell.rc Hunspell.sln Hunspell.vcproj + all: all-am .SUFFIXES: diff --git a/src/win_api/config.h b/src/win_api/config.h new file mode 100644 index 0000000..1e5a44f --- /dev/null +++ b/src/win_api/config.h @@ -0,0 +1,214 @@ +/* config.h.in. Generated from configure.ac by autoheader. */ + +/* Define to one of `_getb67', `GETB67', `getb67' for Cray-2 and Cray-YMP + systems. This function is required for `alloca.c' support on those systems. + */ +#define CRAY_STACKSEG_END 1 + +/* Define to 1 if using `alloca.c'. */ +#define C_ALLOCA 1 + +/* Define to 1 if translation of program messages to the user's native + language is requested. */ +#define ENABLE_NLS 1 + +/* Define to 1 if you have `alloca', as a function or macro. */ +#define HAVE_ALLOCA 1 + +/* Define to 1 if you have <alloca.h> and it should be used (not on Ultrix). + */ +#define HAVE_ALLOCA_H 1 + +/* Define to 1 if you have the <argz.h> header file. */ +#define HAVE_ARGZ_H 1 + +/* "Define if you have the <curses.h> header" */ +#define HAVE_CURSES_H 1 + +/* Define if the GNU dcgettext() function is already present or preinstalled. + */ +#define HAVE_DCGETTEXT 1 + +/* Define to 1 if you have the <dlfcn.h> header file. */ +#define HAVE_DLFCN_H 1 + +/* Define to 1 if you have the <error.h> header file. */ +#define HAVE_ERROR_H 1 + +/* Define to 1 if you have the <fcntl.h> header file. */ +#define HAVE_FCNTL_H 1 + +/* Define to 1 if you have the `feof_unlocked' function. */ +#define HAVE_FEOF_UNLOCKED 1 + +/* Define to 1 if you have the `fgets_unlocked' function. */ +#define HAVE_FGETS_UNLOCKED 1 + +/* Define to 1 if you have the `getcwd' function. */ +#define HAVE_GETCWD 1 + +/* Define to 1 if you have the `getc_unlocked' function. */ +#define HAVE_GETC_UNLOCKED 1 + +/* Define to 1 if you have the `getegid' function. */ +#define HAVE_GETEGID 1 + +/* Define to 1 if you have the `geteuid' function. */ +#define HAVE_GETEUID 1 + +/* Define to 1 if you have the `getgid' function. */ +#define HAVE_GETGID 1 + +/* Define to 1 if you have the `getpagesize' function. */ +#define HAVE_GETPAGESIZE 1 + +/* Define if the GNU gettext() function is already present or preinstalled. */ +#define HAVE_GETTEXT 1 + +/* Define to 1 if you have the `getuid' function. */ +#define HAVE_GETUID 1 + +/* Define if you have the iconv() function. */ +#define HAVE_ICONV 1 + +/* Define to 1 if you have the <inttypes.h> header file. */ +#define HAVE_INTTYPES_H 1 + +/* Define if you have <langinfo.h> and nl_langinfo(CODESET). */ +#define HAVE_LANGINFO_CODESET 1 + +/* Define if your <locale.h> file defines LC_MESSAGES. */ +#define HAVE_LC_MESSAGES 1 + +/* Define to 1 if you have the <libintl.h> header file. */ +#define HAVE_LIBINTL_H 1 + +/* Define to 1 if you have the <limits.h> header file. */ +#define HAVE_LIMITS_H 1 + +/* Define to 1 if you have the <locale.h> header file. */ +#define HAVE_LOCALE_H 1 + +/* Define to 1 if your system has a GNU libc compatible `malloc' function, and + to 0 otherwise. */ +#define HAVE_MALLOC 1 + +/* Define to 1 if you have the <malloc.h> header file. */ +#define HAVE_MALLOC_H 1 + +/* Define to 1 if you have the `memchr' function. */ +#define HAVE_MEMCHR 1 + +/* Define to 1 if you have the <memory.h> header file. */ +#define HAVE_MEMORY_H 1 + +/* Define to 1 if you have the `mempcpy' function. */ +#define HAVE_MEMPCPY 1 + +/* Define to 1 if you have a working `mmap' system call. */ +#define HAVE_MMAP 1 + +/* Define to 1 if you have the `munmap' function. */ +#define HAVE_MUNMAP 1 + +/* "Define if you have the <ncursesw/curses.h> header" */ +#define HAVE_NCURSESW_H 1 + +/* Define to 1 if you have the <nl_types.h> header file. */ +#define HAVE_NL_TYPES_H 1 + +/* Define to 1 if you have the `putenv' function. */ +#define HAVE_PUTENV 1 + +/* "Define if you have fancy command input editing with Readline" */ +#define HAVE_READLINE 1 + +/* Define to 1 if you have the `setenv' function. */ +#define HAVE_SETENV 1 + +/* Define to 1 if you have the `setlocale' function. */ +#define HAVE_SETLOCALE 1 + +/* Define to 1 if you have the <stddef.h> header file. */ +#define HAVE_STDDEF_H 1 + +/* Define to 1 if you have the <stdint.h> header file. */ +#define HAVE_STDINT_H 1 + +/* Define to 1 if you have the <stdlib.h> header file. */ +#define HAVE_STDLIB_H 1 + +/* Define to 1 if you have the `stpcpy' function. */ +#define HAVE_STPCPY 1 + +/* Define to 1 if you have the `strcasecmp' function. */ +#define HAVE_STRCASECMP 1 + +/* Define to 1 if you have the `strchr' function. */ +#define HAVE_STRCHR 1 + +/* Define to 1 if you have the `strdup' function. */ +#define HAVE_STRDUP 1 + +/* Define to 1 if you have the <strings.h> header file. */ +#define HAVE_STRINGS_H 1 + +/* Define to 1 if you have the <string.h> header file. */ +#define HAVE_STRING_H 1 + +/* Define to 1 if you have the `strstr' function. */ +#define HAVE_STRSTR 1 + +/* Define to 1 if you have the `strtoul' function. */ +#define HAVE_STRTOUL 1 + +/* Define to 1 if you have the <sys/param.h> header file. */ +#define HAVE_SYS_PARAM_H 1 + +/* Define to 1 if you have the <sys/stat.h> header file. */ +#define HAVE_SYS_STAT_H 1 + +/* Define to 1 if you have the <sys/types.h> header file. */ +#define HAVE_SYS_TYPES_H 1 + +/* Define to 1 if you have the `tsearch' function. */ +#define HAVE_TSEARCH 1 + +/* Define to 1 if you have the <unistd.h> header file. */ +#define HAVE_UNISTD_H 1 + +/* Define to 1 if you have the `__argz_count' function. */ +#define HAVE___ARGZ_COUNT 1 + +/* Define to 1 if you have the `__argz_next' function. */ +#define HAVE___ARGZ_NEXT 1 + +/* Define to 1 if you have the `__argz_stringify' function. */ +#define HAVE___ARGZ_STRINGIFY 1 + +/* "Define if you use exterimental functions" */ +#undef HUNSPELL_EXPERIMENTAL + +/* "Define if you need warning messages" */ +#undef HUNSPELL_WARNING_ON + +/* Define as const if the declaration of iconv() needs const. */ +#define ICONV_CONST 1 + +/* Name of package */ +#define PACKAGE + +/* Define to the address where bug reports for this package should be sent. */ +#define PACKAGE_BUGREPORT + +/* Define to the full name of this package. */ +#define PACKAGE_NAME + +/* Define to the full name and version of this package. */ +#define PACKAGE_STRING + +/* Define to the one symbol short name of this package. */ +#define PACKAGE_TARNAME + +/* Define to the version of this package. */ +#define PACKAGE_VERSION diff --git a/tests/1706659.aff b/tests/1706659.aff new file mode 100644 index 0000000..ec14953 --- /dev/null +++ b/tests/1706659.aff @@ -0,0 +1,13 @@ +# COMPOUNDRULE test file by Björn Jacke +SET ISO8859-1 +TRY esijanrtolcdugmphbyfvkwqxz + +SFX A Y 5 +SFX A 0 e . +SFX A 0 er . +SFX A 0 en . +SFX A 0 em . +SFX A 0 es . + +COMPOUNDRULE 1 +COMPOUNDRULE vw diff --git a/tests/1706659.dic b/tests/1706659.dic new file mode 100644 index 0000000..32d461f --- /dev/null +++ b/tests/1706659.dic @@ -0,0 +1,4 @@ +3 +arbeits/v +scheu/Aw +farbig/A diff --git a/tests/1706659.test b/tests/1706659.test new file mode 100755 index 0000000..7f44369 --- /dev/null +++ b/tests/1706659.test @@ -0,0 +1,4 @@ +#!/bin/sh +DIR="`dirname $0`" +NAME="`basename $0 .test`" +$DIR/test.sh $NAME diff --git a/tests/1706659.wrong b/tests/1706659.wrong new file mode 100644 index 0000000..799dd31 --- /dev/null +++ b/tests/1706659.wrong @@ -0,0 +1,3 @@ +arbeitsfarbig +arbeitsfarbige +arbeitsfarbiger diff --git a/tests/Makefile.am b/tests/Makefile.am index 8e9e524..8cddb70 100644 --- a/tests/Makefile.am +++ b/tests/Makefile.am @@ -78,7 +78,10 @@ ignoreutf.test \ 1463589_utf.test \ IJ.test \ i68568.test \ -i68568utf.test +i68568utf.test \ +1706659.test \ +digits_in_words.test \ +colons_in_words.test # infixes.test distclean-local: @@ -467,7 +470,18 @@ i68568.wrong \ i68568utf.aff \ i68568utf.dic \ i68568utf.test \ -i68568utf.wrong +i68568utf.wrong \ +1706659.aff \ +1706659.dic \ +1706659.test \ +1706659.wrong \ +digits_in_words.aff \ +digits_in_words.dic \ +digits_in_words.test \ +digits_in_words.wrong \ +colons_in_words.aff \ +colons_in_words.dic \ +colons_in_words.test # infixes.aff # infixes.dic # infixes.good diff --git a/tests/Makefile.in b/tests/Makefile.in index 955712a..ee1ec37 100644 --- a/tests/Makefile.in +++ b/tests/Makefile.in @@ -260,7 +260,10 @@ ignoreutf.test \ 1463589_utf.test \ IJ.test \ i68568.test \ -i68568utf.test +i68568utf.test \ +1706659.test \ +digits_in_words.test \ +colons_in_words.test EXTRA_DIST = \ test.sh \ @@ -645,7 +648,18 @@ i68568.wrong \ i68568utf.aff \ i68568utf.dic \ i68568utf.test \ -i68568utf.wrong +i68568utf.wrong \ +1706659.aff \ +1706659.dic \ +1706659.test \ +1706659.wrong \ +digits_in_words.aff \ +digits_in_words.dic \ +digits_in_words.test \ +digits_in_words.wrong \ +colons_in_words.aff \ +colons_in_words.dic \ +colons_in_words.test all: all-am diff --git a/tests/colons_in_words.aff b/tests/colons_in_words.aff new file mode 100644 index 0000000..d080226 --- /dev/null +++ b/tests/colons_in_words.aff @@ -0,0 +1,3 @@ +# Colons in Finnish and Swedish words. Problem reported by Lars Aronsson. +# Parsing test (src/parsers) +WORDCHARS : diff --git a/tests/colons_in_words.dic b/tests/colons_in_words.dic new file mode 100644 index 0000000..bfea1cc --- /dev/null +++ b/tests/colons_in_words.dic @@ -0,0 +1,4 @@ +2 +c:a +S:t +foo diff --git a/tests/colons_in_words.test b/tests/colons_in_words.test new file mode 100755 index 0000000..7f44369 --- /dev/null +++ b/tests/colons_in_words.test @@ -0,0 +1,4 @@ +#!/bin/sh +DIR="`dirname $0`" +NAME="`basename $0 .test`" +$DIR/test.sh $NAME diff --git a/tests/digits_in_words.aff b/tests/digits_in_words.aff new file mode 100644 index 0000000..18a42f6 --- /dev/null +++ b/tests/digits_in_words.aff @@ -0,0 +1,9 @@ +# Digits in words, handled by COMPOUNDRULE. +# 1-jährig, 2-jährig, 100-jährig etc. +SET UTF-8 +COMPOUNDMIN 1 +# recognize ab, aab, aaab etc. compounds (a=digits, b=-jährig, see dic file) +COMPOUNDRULE 1 +COMPOUNDRULE a*b +ONLYINCOMPOUND c +WORDCHARS 0123456789- diff --git a/tests/digits_in_words.dic b/tests/digits_in_words.dic new file mode 100644 index 0000000..deeaece --- /dev/null +++ b/tests/digits_in_words.dic @@ -0,0 +1,12 @@ +11 +0/a +1/a +2/a +3/a +4/a +5/a +6/a +7/a +8/a +9/a +-jährig/bc diff --git a/tests/digits_in_words.test b/tests/digits_in_words.test new file mode 100755 index 0000000..cde7c54 --- /dev/null +++ b/tests/digits_in_words.test @@ -0,0 +1,4 @@ +#!/bin/sh +DIR="`dirname $0`" +NAME="`basename $0 .test`" +$DIR/test.sh $NAME -i utf-8 diff --git a/tests/digits_in_words.wrong b/tests/digits_in_words.wrong new file mode 100644 index 0000000..aeaf6ce --- /dev/null +++ b/tests/digits_in_words.wrong @@ -0,0 +1 @@ +-jährig -- Alioth's /usr/local/bin/git-commit-notice on /srv/git.debian.org/git/pkg-openoffice/hunspell.git
