recoll / Code / Diff of /src/common/unacpp.cpp

Diff of /src/common/unacpp.cpp [913dff] .. [08deef]

Switch to unified view


...
    if (cout)
    free(cout);
    return true;
}

// Functions to determine upper-case or accented status could be implemented
// hugely more efficiently inside the unac c code, but there only used for
// testing user-entered terms, so we don't really care.
bool unaciscapital(const string& in)
{
    LOGDEB2(("unaciscapital: [%s]\n", in.c_str()));
    if (in.empty())
    return false;
    Utf8Iter it(in);
    string shorter;
    it.appendchartostring(shorter);

    string lower;
    if (!unacmaybefold(shorter, lower, "UTF-8", UNACOP_FOLD)) {
    LOGINFO(("unaciscapital: unac/fold failed for [%s]\n", in.c_str()));
    return false;
    } 




    Utf8Iter it1(lower);

    if (*it != *it1)
  return true;
    else
  return false;
}
bool unachasuppercase(const string& in)
{
    LOGDEB2(("unachasuppercase: [%s]\n", in.c_str()));
    if (in.empty())
  return false;

    string lower;
    if (!unacmaybefold(in, lower, "UTF-8", UNACOP_FOLD)) {
  LOGINFO(("unachasuppercase: unac/fold failed for [%s]\n", in.c_str()));
  return false;
    } 
    if (lower != in)
  return true;
    else
  return false;
}
bool unachasaccents(const string& in)
{
    LOGDEB2(("unachasaccents: [%s]\n", in.c_str()));
    if (in.empty())
  return false;

    string noac;
    if (!unacmaybefold(in, noac, "UTF-8", UNACOP_UNAC)) {
  LOGINFO(("unachasaccents: unac/unac failed for [%s]\n", in.c_str()));
  return false;
    } 
    if (noac != in)
    return true;
    else
    return false;
}

...

static char *thisprog;

static char usage [] = "\n"
    "[-c|-C] <encoding> <infile> <outfile>\n"
    "   Default : unaccent\n"
    "   -c : unaccent and casefold\n"
    "   -C : casefold only\n"
    "-t <string> test string as capitalized, upper-case anywhere, accents\n"
    "   the parameter is supposedly utf-8 so this can only work in an utf-8\n"
    "   locale\n"
    "\n";

;

static void
Usage(void)
{
    fprintf(stderr, "%s: usage: %s\n", thisprog, usage);
    exit(1);
}

static int     op_flags;
#define OPT_c     0x2 
#define OPT_C     0x4 
#define OPT_t     0x8

int main(int argc, char **argv)
{
    UnacOp op = UNACOP_UNAC;

...
        Usage();
    while (**argv)
        switch (*(*argv)++) {
        case 'c':   op_flags |= OPT_c; break;
        case 'C':   op_flags |= OPT_C; break;
      case 't':   op_flags |= OPT_t; break;
        default: Usage();   break;
        }
    argc--; argv++;
    }

    if (op_flags & OPT_t) {
  if (argc != 1)
      Usage();
  string in = *argv++;argc--;
  bool capital, upper, accent;
  capital = unaciscapital(in);
  upper = unachasuppercase(in);
  accent = unachasaccents(in);
  cout << "[" << in << "] : " << 
      "capitalized: " << (capital ? "Yes. " : "No. ") <<
      "has uppercase: " << (upper ? "Yes. " : "No. ") <<
      "has accents: " << (accent ? "Yes. " : "No. ") << 
      endl;
  return 0;
    } else {
  if (argc != 3)
      Usage();
  if (op_flags & OPT_c) {
        op = UNACOP_UNACFOLD;
  } else if (op_flags & OPT_C) {
        op = UNACOP_FOLD;
  }





  const char *encoding = *argv++; argc--;
  string ifn = *argv++; argc--;
  if (!ifn.compare("stdin"))
        ifn.clear();
  const char *ofn = *argv++; argc--;

  string reason;
  (void)recollinit(RCLINIT_NONE, 0, 0, reason, 0);

  string odata;
  if (!file_to_string(ifn, odata)) {
        cerr << "file_to_string " << ifn << " : " << odata << endl;
        return 1;
  }
  string ndata;
  if (!unacmaybefold(odata, ndata, encoding, op)) {
        cerr << "unac: " << ndata << endl;
        return 1;
  }
    
  int fd;
  if (strcmp(ofn, "stdout")) {
        fd = open(ofn, O_CREAT|O_EXCL|O_WRONLY, 0666);
  } else {
        fd = 1;
  }
  if (fd < 0) {
        cerr << "Open/Create " << ofn << " failed: " << strerror(errno) 
       << endl;
        return 1;
  }
  if (write(fd, ndata.c_str(), ndata.length()) != (int)ndata.length()) {
        cerr << "Write(2) failed: " << strerror(errno)  << endl;
      return 1;
  }
  close(fd);
    return 0;
    }


}

#endif

	a/src/common/unacpp.cpp		b/src/common/unacpp.cpp
	...		...
61	if (cout)	61	if (cout)
62	free(cout);	62	free(cout);
63	return true;	63	return true;
64	}	64	}
65		65
		66	// Functions to determine upper-case or accented status could be implemented
		67	// hugely more efficiently inside the unac c code, but there only used for
		68	// testing user-entered terms, so we don't really care.
66	bool unaciscapital(const string& in)	69	bool unaciscapital(const string& in)
67	{	70	{
		71	LOGDEB2(("unaciscapital: [%s]\n", in.c_str()));
68	if (in.empty())	72	if (in.empty())
69	return false;	73	return false;
70	Utf8Iter it(in);	74	Utf8Iter it(in);
71	string shorter;	75	string shorter;
72	it.appendchartostring(shorter);	76	it.appendchartostring(shorter);
73		77
74	string noacterm, noaclowterm;	78	string lower;
75	if (!unacmaybefold(shorter, noacterm, "UTF-8", UNACOP_UNAC)) {	79	if (!unacmaybefold(shorter, lower, "UTF-8", UNACOP_FOLD)) {
76	LOGINFO(("unaciscapital: unac failed for [%s]\n", in.c_str()));	80	LOGINFO(("unaciscapital: unac/fold failed for [%s]\n", in.c_str()));
77	return false;	81	return false;
78	}	82	}
79	if (!unacmaybefold(noacterm, noaclowterm, "UTF-8", UNACOP_UNACFOLD)) {
80	LOGINFO(("unaciscapital: unacfold failed for [%s]\n", in.c_str()));
81	return false;
82	}
83	Utf8Iter it1(noacterm);	83	Utf8Iter it1(lower);
84	Utf8Iter it2(noaclowterm);
85	if (it1 != it2)	84	if (it != it1)
		85	return true;
		86	else
		87	return false;
		88	}
		89	bool unachasuppercase(const string& in)
		90	{
		91	LOGDEB2(("unachasuppercase: [%s]\n", in.c_str()));
		92	if (in.empty())
		93	return false;
		94
		95	string lower;
		96	if (!unacmaybefold(in, lower, "UTF-8", UNACOP_FOLD)) {
		97	LOGINFO(("unachasuppercase: unac/fold failed for [%s]\n", in.c_str()));
		98	return false;
		99	}
		100	if (lower != in)
		101	return true;
		102	else
		103	return false;
		104	}
		105	bool unachasaccents(const string& in)
		106	{
		107	LOGDEB2(("unachasaccents: [%s]\n", in.c_str()));
		108	if (in.empty())
		109	return false;
		110
		111	string noac;
		112	if (!unacmaybefold(in, noac, "UTF-8", UNACOP_UNAC)) {
		113	LOGINFO(("unachasaccents: unac/unac failed for [%s]\n", in.c_str()));
		114	return false;
		115	}
		116	if (noac != in)
86	return true;	117	return true;
87	else	118	else
88	return false;	119	return false;
89	}	120	}
90		121
	...		...
105		136
106	static char *thisprog;	137	static char *thisprog;
107		138
108	static char usage [] = "\n"	139	static char usage [] = "\n"
109	"[-c\|-C] <encoding> <infile> <outfile>\n"	140	"[-c\|-C] <encoding> <infile> <outfile>\n"
110	" Default : unaccent\n"	141	" Default : unaccent\n"
111	" -c : unaccent and casefold\n"	142	" -c : unaccent and casefold\n"
112	" -C : casefold only\n"	143	" -C : casefold only\n"
		144	"-t <string> test string as capitalized, upper-case anywhere, accents\n"
		145	" the parameter is supposedly utf-8 so this can only work in an utf-8\n"
		146	" locale\n"
113	"\n";	147	"\n";
114
115	;	148	;
		149
116	static void	150	static void
117	Usage(void)	151	Usage(void)
118	{	152	{
119	fprintf(stderr, "%s: usage: %s\n", thisprog, usage);	153	fprintf(stderr, "%s: usage: %s\n", thisprog, usage);
120	exit(1);	154	exit(1);
121	}	155	}
122		156
123	static int op_flags;	157	static int op_flags;
124	#define OPT_c 0x2	158	#define OPT_c 0x2
125	#define OPT_C 0x4	159	#define OPT_C 0x4
		160	#define OPT_t 0x8
126		161
127	int main(int argc, char **argv)	162	int main(int argc, char **argv)
128	{	163	{
129	UnacOp op = UNACOP_UNAC;	164	UnacOp op = UNACOP_UNAC;
130		165
	...		...
138	Usage();	173	Usage();
139	while (**argv)	174	while (**argv)
140	switch ((argv)++) {	175	switch ((argv)++) {
141	case 'c': op_flags \|= OPT_c; break;	176	case 'c': op_flags \|= OPT_c; break;
142	case 'C': op_flags \|= OPT_C; break;	177	case 'C': op_flags \|= OPT_C; break;
		178	case 't': op_flags \|= OPT_t; break;
143	default: Usage(); break;	179	default: Usage(); break;
144	}	180	}
145	argc--; argv++;	181	argc--; argv++;
146	}	182	}
147		183
148	if (op_flags & OPT_c) {	184	if (op_flags & OPT_t) {
		185	if (argc != 1)
		186	Usage();
		187	string in = *argv++;argc--;
		188	bool capital, upper, accent;
		189	capital = unaciscapital(in);
		190	upper = unachasuppercase(in);
		191	accent = unachasaccents(in);
		192	cout << "[" << in << "] : " <<
		193	"capitalized: " << (capital ? "Yes. " : "No. ") <<
		194	"has uppercase: " << (upper ? "Yes. " : "No. ") <<
		195	"has accents: " << (accent ? "Yes. " : "No. ") <<
		196	endl;
		197	return 0;
		198	} else {
		199	if (argc != 3)
		200	Usage();
		201	if (op_flags & OPT_c) {
149	op = UNACOP_UNACFOLD;	202	op = UNACOP_UNACFOLD;
150	} else if (op_flags & OPT_C) {	203	} else if (op_flags & OPT_C) {
151	op = UNACOP_FOLD;	204	op = UNACOP_FOLD;
152	}	205	}
153		206
154	if (argc != 3) {
155	Usage();
156	}
157
158	const char encoding = argv++; argc--;	207	const char encoding = argv++; argc--;
159	string ifn = *argv++; argc--;	208	string ifn = *argv++; argc--;
160	if (!ifn.compare("stdin"))	209	if (!ifn.compare("stdin"))
161	ifn.clear();	210	ifn.clear();
162	const char ofn = argv++; argc--;	211	const char ofn = argv++; argc--;
163		212
164	string reason;	213	string reason;
165	(void)recollinit(RCLINIT_NONE, 0, 0, reason, 0);	214	(void)recollinit(RCLINIT_NONE, 0, 0, reason, 0);
166		215
167	string odata;	216	string odata;
168	if (!file_to_string(ifn, odata)) {	217	if (!file_to_string(ifn, odata)) {
169	cerr << "file_to_string " << ifn << " : " << odata << endl;	218	cerr << "file_to_string " << ifn << " : " << odata << endl;
170	return 1;	219	return 1;
171	}	220	}
172	string ndata;	221	string ndata;
173	if (!unacmaybefold(odata, ndata, encoding, op)) {	222	if (!unacmaybefold(odata, ndata, encoding, op)) {
174	cerr << "unac: " << ndata << endl;	223	cerr << "unac: " << ndata << endl;
175	return 1;	224	return 1;
176	}	225	}
177		226
178	int fd;	227	int fd;
179	if (strcmp(ofn, "stdout")) {	228	if (strcmp(ofn, "stdout")) {
180	fd = open(ofn, O_CREAT\|O_EXCL\|O_WRONLY, 0666);	229	fd = open(ofn, O_CREAT\|O_EXCL\|O_WRONLY, 0666);
181	} else {	230	} else {
182	fd = 1;	231	fd = 1;
183	}	232	}
184	if (fd < 0) {	233	if (fd < 0) {
185	cerr << "Open/Create " << ofn << " failed: " << strerror(errno)	234	cerr << "Open/Create " << ofn << " failed: " << strerror(errno)
186	<< endl;	235	<< endl;
187	return 1;	236	return 1;
188	}	237	}
189	if (write(fd, ndata.c_str(), ndata.length()) != (int)ndata.length()) {	238	if (write(fd, ndata.c_str(), ndata.length()) != (int)ndata.length()) {
190	cerr << "Write(2) failed: " << strerror(errno) << endl;	239	cerr << "Write(2) failed: " << strerror(errno) << endl;
		240	return 1;
		241	}
		242	close(fd);
191	return 1;	243	return 0;
192	}	244	}
193	close(fd);
194	return 0;
195	}	245	}
196		246
197	#endif	247	#endif