7314850954

Committed 24 Dec 2023 01:12PM UTC coverage: 88.826% (+2.5%) from 86.336%

Build # 7314850954

Build Type

push

github

Committed by

tsjensen

Commit Message

Use -ggdb3 option for more detailed debug info

Run Details

2869 of 3408 branches covered (0.0%)

Branch coverage included in aggregate %.

4619 of 5022 relevant lines covered (91.98%)

202175.9 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

90.21

/src/unicode.c

/*
 * boxes - Command line filter to draw/remove ASCII boxes around text
 * Copyright (c) 1999-2023 Thomas Jensen and the boxes contributors
 *
 * This program is free software: you can redistribute it and/or modify it under the terms of the GNU General Public
 * License, version 3, as published by the Free Software Foundation.
 * This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied
 * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for more
 * details.
 * You should have received a copy of the GNU General Public License along with this program.
 * If not, see <https://www.gnu.org/licenses/>.
 *
* * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * *
 */

/*
 * Functions and constants for handling unicode strings with libunistring.
 */

#include "config.h"
#include <errno.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>

#include <uniconv.h>
#include <unictype.h>
#include <unistr.h>

#include "boxes.h"
#include "tools.h"
#include "unicode.h"



/* effective character encoding of input and output text */
const char *encoding;

/* ucs4_t character '\t' (tab)  */
const ucs4_t char_tab = 0x00000009;

/* ucs4_t character ' '  (space) */
const ucs4_t char_space = 0x00000020;

/* ucs4_t character '\r' (carriage return) */
const ucs4_t char_cr = 0x0000000d;

/* ucs4_t character '\n' (newline) */
const ucs4_t char_newline = 0x0000000a;

/* ucs4_t character 0x1b (escape)  */
const ucs4_t char_esc = 0x0000001b;

/* ucs4_t character '\0' (zero) */
const ucs4_t char_nul = 0x00000000;



int is_char_at(const uint32_t *text, const size_t idx, const ucs4_t expected_char)
{
    return text != NULL && u32_cmp(text + idx, &expected_char, 1) == 0;
}



void set_char_at(uint32_t *text, const size_t idx, const ucs4_t char_to_set)
{
    u32_set(text + idx, char_to_set, 1);
}



int is_empty(const uint32_t *text)
{
    return text == NULL || is_char_at(text, 0, char_nul);
}



int u32_is_blank(const uint32_t *text)
{
    if (is_empty(text)) {
        return 1;
    }

    for (const uint32_t *c = text; *c != char_nul; c++) {
        if (!is_blank(*c)) {
            return 0;
        }
    }
    return 1;
}



int is_ascii_printable(const ucs4_t c)
{
    return c >= 0x20 && c < 0x7f;
}



int is_allowed_anywhere(const ucs4_t c)
{
    /* ESC, CR, LF, and TAB are control characters */
    return !uc_is_cntrl(c) || c == char_tab || c == char_cr || c == char_newline || c == char_esc;
}



int is_allowed_in_shape(const ucs4_t c)
{
    return is_allowed_anywhere(c) && c != char_cr && c != char_newline;
}



int is_allowed_in_sample(const ucs4_t c)
{
    return is_allowed_anywhere(c);
}



int is_allowed_in_filename(const ucs4_t c)
{
    return is_allowed_anywhere(c) && c != char_cr && c != char_newline && c != char_esc;
}



int is_allowed_in_kv_string(const ucs4_t c)
{
    return is_allowed_anywhere(c) && c != char_cr && c != char_newline && c != char_esc;
}



int is_blank(const ucs4_t c)
{
    return c == char_tab || uc_is_blank(c);
}



uint32_t *new_empty_string32()
{
    return (uint32_t *) calloc(1, sizeof(uint32_t));
}



ucs4_t to_utf32(char ascii)
{
    ucs4_t c = char_nul;
    if (ascii >= 0x20 && ascii < 0x7f) {
        char *bytes = (char *) (&c);
        bytes[0] = ascii;
    }
    return c;
}



uint32_t *advance_next32(const uint32_t *s, size_t *invis)
{
    if (is_empty(s)) {
        return (uint32_t *) s;
    }

    int ansipos = 0;
    (*invis) = 0;
    ucs4_t c;
    const uint32_t *rest = s;
    while ((rest = u32_next(&c, rest))) {
        if (ansipos == 0 && c == char_esc) {
            /* Found an ESC char, count it as invisible and move 1 forward in the detection of CSI sequences */
            (*invis)++;
            ansipos++;
        } else if (ansipos == 1 && (c == '[' || c == '(')) {
            /* Found '[' char after ESC. A CSI sequence has started. */
            (*invis)++;
            ansipos++;
        } else if (ansipos == 1 && c >= 0x40 && c <= 0x5f) { /* between '@' and '_' (mostly uppercase letters) */
            /* Found a byte designating the end of a two-byte escape sequence */
            (*invis)++;
            ansipos = 0;
            break;
        } else if (ansipos == 2) {
            /* Inside CSI sequence - Keep counting chars as invisible */
            (*invis)++;

            /* A char between 0x40 and 0x7e signals the end of an CSI or escape sequence */
            if (c >= 0x40 && c <= 0x7e) {
                ansipos = 0;
                break;
            }
        } else {
            break;
        }
    }
    if (rest == NULL) {
        rest = s + u32_strlen(s);
    }
    return (uint32_t *) rest;
}



uint32_t *u32_strconv_from_input(const char *src)
{
    return u32_strconv_from_arg(src, encoding);
}



uint32_t *u32_strconv_from_arg(const char *src, const char *sourceEncoding)
{
    if (src == NULL) {
        return NULL;
    }
    if (src[0] == '\0') {
        return new_empty_string32();
    }

    uint32_t *result = u32_strconv_from_encoding(
            src,                    /* the source string to convert */
            sourceEncoding,         /* the character encoding from which to convert */
            iconveh_question_mark); /* produce one question mark '?' per unconvertible character */

    if (result == NULL) {
        fprintf(stderr, "%s: failed to convert from '%s' to UTF-32: %s\n", PROJECT, sourceEncoding, strerror(errno));
    }
    return result;
}



char *u32_strconv_to_output(const uint32_t *src)
{
    return u32_strconv_to_arg(src, encoding);
}



char *u32_strconv_to_arg(const uint32_t *src, const char *targetEncoding)
{
    if (src == NULL) {
        return NULL;
    }
    if (is_empty(src)) {
        return strdup("");
    }

    char *result = u32_strconv_to_encoding(
            src,                    /* the source string to convert */
            targetEncoding,         /* the character encoding to which to convert */
            iconveh_question_mark); /* produce one question mark '?' per unconvertible character */

    if (result == NULL) {
        fprintf(stderr, "%s: failed to convert from UTF-32 to '%s': %s\n", PROJECT, targetEncoding, strerror(errno));
    }
    return result;
}



const char *check_encoding(const char *manual_encoding, const char *system_encoding)
{
    if (manual_encoding != NULL) {
        uint32_t *unicode = u32_strconv_from_encoding(" ", manual_encoding, iconveh_error);
        if (unicode != NULL) {
            BFREE(unicode);
            return manual_encoding;
        }
        fprintf(stderr, "%s: Invalid character encoding: %s - falling back to %s\n",
                PROJECT, manual_encoding, system_encoding);
        fflush(stderr);
    }
    return system_encoding;
}



char *to_utf8(uint32_t *src)
{
    if (src == NULL) {
        return NULL;
    }
    if (is_empty(src)) {
        return (char *) strdup("");
    }
    char *result = u32_strconv_to_encoding(src, "UTF-8", iconveh_error);
    if (result == NULL) {
        bx_fprintf(stderr, "%s: failed to convert a string to UTF-8: %s\n", PROJECT, strerror(errno));
        return NULL;
    }
    return result;
}



uint32_t *u32_nspaces(const size_t n)
{
    uint32_t *result = (uint32_t *) malloc((n + 1) * sizeof(uint32_t));
    if (result == NULL) {
        perror(PROJECT);
        return NULL;
    }
    if (n > 0) {
        u32_set(result, char_space, n);
    }
    set_char_at(result, n, char_nul);
    return result;
}



uint32_t *u32_strnrstr(const uint32_t *haystack, const uint32_t *needle, const size_t needle_len)
{
    if (is_empty(needle)) {
        return (uint32_t *) haystack;
    }
    if (is_empty(haystack)) {
        return NULL;
    }

    uint32_t *p = u32_strrchr(haystack, needle[0]);
    if (!p) {
        return NULL;
    }

    while (p >= haystack) {
        if (u32_strncmp(p, needle, needle_len) == 0) {
            return p;
        }
        --p;
    }

    return NULL;
}



void u32_insert_space_at(uint32_t **s, const size_t idx, const size_t n)
{
    if (s == NULL || n == 0) {
        return;
    }

    size_t len = u32_strlen(*s);
    size_t x = idx;
    if (idx > len) {
        x = len;
    }

    *s = (uint32_t *) realloc(*s, (len + 1 + n) * sizeof(uint32_t));
    u32_move(*s + x + n, *s + x, len - x);
    u32_set(*s + x, char_space, n);
}


/* vim: set cindent sw=4: */

1	/*
2	* boxes - Command line filter to draw/remove ASCII boxes around text
3	* Copyright (c) 1999-2023 Thomas Jensen and the boxes contributors
4	*
5	* This program is free software: you can redistribute it and/or modify it under the terms of the GNU General Public
6	* License, version 3, as published by the Free Software Foundation.
7	* This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied
8	* warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
9	* details.
10	* You should have received a copy of the GNU General Public License along with this program.
11	* If not, see <https://www.gnu.org/licenses/>.
12	*
13	* * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * *
14	*/
15
16	/*
17	* Functions and constants for handling unicode strings with libunistring.
18	*/
19
20	#include "config.h"
21	#include <errno.h>
22	#include <stdio.h>
23	#include <stdlib.h>
24	#include <string.h>
25
26	#include <uniconv.h>
27	#include <unictype.h>
28	#include <unistr.h>
29
30	#include "boxes.h"
31	#include "tools.h"
32	#include "unicode.h"
33
34
35
36	/* effective character encoding of input and output text */
37	const char *encoding;
38
39	/* ucs4_t character '\t' (tab) */
40	const ucs4_t char_tab = 0x00000009;
41
42	/* ucs4_t character ' ' (space) */
43	const ucs4_t char_space = 0x00000020;
44
45	/* ucs4_t character '\r' (carriage return) */
46	const ucs4_t char_cr = 0x0000000d;
47
48	/* ucs4_t character '\n' (newline) */
49	const ucs4_t char_newline = 0x0000000a;
50
51	/* ucs4_t character 0x1b (escape) */
52	const ucs4_t char_esc = 0x0000001b;
53
54	/* ucs4_t character '\0' (zero) */
55	const ucs4_t char_nul = 0x00000000;
56
57
58
59	int is_char_at(const uint32_t *text, const size_t idx, const ucs4_t expected_char)	19,328,773✔
60	{
61	return text != NULL && u32_cmp(text + idx, &expected_char, 1) == 0;	19,328,773!
62	}
63
64
65
66	void set_char_at(uint32_t *text, const size_t idx, const ucs4_t char_to_set)	388,460✔
67	{
68	u32_set(text + idx, char_to_set, 1);	388,460✔
69	}	388,460✔
70
71
72
73	int is_empty(const uint32_t *text)	19,321,505✔
74	{
75	return text == NULL \|\| is_char_at(text, 0, char_nul);	19,321,505✔
76	}
77
78
79
80	int u32_is_blank(const uint32_t *text)	112✔
81	{
82	if (is_empty(text)) {	112✔
83	return 1;	2✔
84	}
85
86	for (const uint32_t c = text; c != char_nul; c++) {	594✔
87	if (!is_blank(*c)) {	484✔
88	return 0;	×
89	}
90	}	242✔
91	return 1;	110✔
92	}	56✔
93
94
95
96	int is_ascii_printable(const ucs4_t c)	19,151,813✔
97	{
98	return c >= 0x20 && c < 0x7f;	19,151,813✔
99	}
100
101
102
103	int is_allowed_anywhere(const ucs4_t c)	20,159,629✔
104	{
105	/* ESC, CR, LF, and TAB are control characters */
106	return !uc_is_cntrl(c) \|\| c == char_tab \|\| c == char_cr \|\| c == char_newline \|\| c == char_esc;	20,159,629✔
107	}
108
109
110
111	int is_allowed_in_shape(const ucs4_t c)	218,998✔
112	{
113	return is_allowed_anywhere(c) && c != char_cr && c != char_newline;	218,998✔
114	}
115
116
117
118	int is_allowed_in_sample(const ucs4_t c)	584,882✔
119	{
120	return is_allowed_anywhere(c);	584,882✔
121	}
122
123
124
125	int is_allowed_in_filename(const ucs4_t c)	492✔
126	{
127	return is_allowed_anywhere(c) && c != char_cr && c != char_newline && c != char_esc;	492✔
128	}
129
130
131
132	int is_allowed_in_kv_string(const ucs4_t c)	143,942✔
133	{
134	return is_allowed_anywhere(c) && c != char_cr && c != char_newline && c != char_esc;	143,942✔
135	}
136
137
138
139	int is_blank(const ucs4_t c)	38,362,014✔
140	{
141	return c == char_tab \|\| uc_is_blank(c);	38,362,014✔
142	}
143
144
145
146	uint32_t *new_empty_string32()	646✔
147	{
148	return (uint32_t *) calloc(1, sizeof(uint32_t));	646✔
149	}
150
151
152
153	ucs4_t to_utf32(char ascii)	6,070✔
154	{
155	ucs4_t c = char_nul;	6,070✔
156	if (ascii >= 0x20 && ascii < 0x7f) {	6,070✔
157	char bytes = (char ) (&c);	6,068✔
158	bytes[0] = ascii;	6,068✔
159	}	3,034✔
160	return c;	6,070✔
161	}
162
163
164
165	uint32_t advance_next32(const uint32_t s, size_t *invis)	19,282,233✔
166	{
167	if (is_empty(s)) {	19,282,233!
168	return (uint32_t *) s;	×
169	}
170
171	int ansipos = 0;	19,282,233✔
172	(*invis) = 0;	19,282,233✔
173	ucs4_t c;
174	const uint32_t *rest = s;	19,282,233✔
175	while ((rest = u32_next(&c, rest))) {	19,621,675✔
176	if (ansipos == 0 && c == char_esc) {	19,621,673✔
177	/* Found an ESC char, count it as invisible and move 1 forward in the detection of CSI sequences */
178	(*invis)++;	63,404✔
179	ansipos++;	63,404✔
180	} else if (ansipos == 1 && (c == '[' \|\| c == '(')) {	19,589,971!
181	/* Found '[' char after ESC. A CSI sequence has started. */
182	(*invis)++;	63,404✔
183	ansipos++;	63,404✔
184	} else if (ansipos == 1 && c >= 0x40 && c <= 0x5f) { /* between '@' and '_' (mostly uppercase letters) */	19,526,567!
185	/* Found a byte designating the end of a two-byte escape sequence */
186	(*invis)++;	×
187	ansipos = 0;	×
188	break;	×
189	} else if (ansipos == 2) {	19,494,865✔
190	/* Inside CSI sequence - Keep counting chars as invisible */
191	(*invis)++;	276,036✔
192
193	/* A char between 0x40 and 0x7e signals the end of an CSI or escape sequence */
194	if (c >= 0x40 && c <= 0x7e) {	276,036✔
195	ansipos = 0;	63,402✔
196	break;	63,402✔
197	}
198	} else {	106,317✔
199	break;	19,218,829✔
200	}
201	}
202	if (rest == NULL) {	19,282,233✔
203	rest = s + u32_strlen(s);	2✔
204	}	1✔
205	return (uint32_t *) rest;	19,282,233✔
206	}	9,641,118✔
207
208
209
210	uint32_t u32_strconv_from_input(const char src)	5,262✔
211	{
212	return u32_strconv_from_arg(src, encoding);	5,262✔
213	}
214
215
216
217	uint32_t u32_strconv_from_arg(const char src, const char *sourceEncoding)	594,580✔
218	{
219	if (src == NULL) {	594,580✔
220	return NULL;	4✔
221	}
222	if (src[0] == '\0') {	594,576✔
223	return new_empty_string32();	126✔
224	}
225
226	uint32_t *result = u32_strconv_from_encoding(	594,450✔
227	src, /* the source string to convert */	297,225✔
228	sourceEncoding, /* the character encoding from which to convert */	297,225✔
229	iconveh_question_mark); /* produce one question mark '?' per unconvertible character */
230
231	if (result == NULL) {	594,450!
232	fprintf(stderr, "%s: failed to convert from '%s' to UTF-32: %s\n", PROJECT, sourceEncoding, strerror(errno));	×
233	}
234	return result;	594,450✔
235	}	297,290✔
236
237
238
239	char u32_strconv_to_output(const uint32_t src)	6,366✔
240	{
241	return u32_strconv_to_arg(src, encoding);	6,366✔
242	}
243
244
245
246	char u32_strconv_to_arg(const uint32_t src, const char *targetEncoding)	7,148✔
247	{
248	if (src == NULL) {	7,148✔
249	return NULL;	×
250	}
251	if (is_empty(src)) {	7,148✔
252	return strdup("");	18✔
253	}
254
255	char *result = u32_strconv_to_encoding(	7,130✔
256	src, /* the source string to convert */	3,565✔
257	targetEncoding, /* the character encoding to which to convert */	3,565✔
258	iconveh_question_mark); /* produce one question mark '?' per unconvertible character */
259
260	if (result == NULL) {	7,130✔
261	fprintf(stderr, "%s: failed to convert from UTF-32 to '%s': %s\n", PROJECT, targetEncoding, strerror(errno));	×
262	}
263	return result;	7,130✔
264	}	3,574✔
265
266
267
268	const char check_encoding(const char manual_encoding, const char *system_encoding)	774✔
269	{
270	if (manual_encoding != NULL) {	774✔
271	uint32_t *unicode = u32_strconv_from_encoding(" ", manual_encoding, iconveh_error);	26✔
272	if (unicode != NULL) {	26✔
273	BFREE(unicode);	24✔
274	return manual_encoding;	24✔
275	}
276	fprintf(stderr, "%s: Invalid character encoding: %s - falling back to %s\n",	3✔
277	PROJECT, manual_encoding, system_encoding);	1✔
278	fflush(stderr);	2✔
279	}	1✔
280	return system_encoding;	750✔
281	}	387✔
282
283
284
285	char to_utf8(uint32_t src)	808✔
286	{
287	if (src == NULL) {	808✔
288	return NULL;	×
289	}
290	if (is_empty(src)) {	808!
291	return (char *) strdup("");	×
292	}
293	char *result = u32_strconv_to_encoding(src, "UTF-8", iconveh_error);	808✔
294	if (result == NULL) {	808!
295	bx_fprintf(stderr, "%s: failed to convert a string to UTF-8: %s\n", PROJECT, strerror(errno));	×
296	return NULL;	×
297	}
298	return result;	808✔
299	}	404✔
300
301
302
303	uint32_t *u32_nspaces(const size_t n)	3,502✔
304	{
305	uint32_t result = (uint32_t ) malloc((n + 1) * sizeof(uint32_t));	3,502✔
306	if (result == NULL) {	3,502!
307	perror(PROJECT);	×
308	return NULL;	×
309	}
310	if (n > 0) {	3,502✔
311	u32_set(result, char_space, n);	2,668✔
312	}	1,334✔
313	set_char_at(result, n, char_nul);	3,502✔
314	return result;	3,502✔
315	}	1,751✔
316
317
318
319	uint32_t u32_strnrstr(const uint32_t haystack, const uint32_t *needle, const size_t needle_len)	11,106✔
320	{
321	if (is_empty(needle)) {	11,106✔
322	return (uint32_t *) haystack;	98✔
323	}
324	if (is_empty(haystack)) {	11,008✔
325	return NULL;	2✔
326	}
327
328	uint32_t *p = u32_strrchr(haystack, needle[0]);	11,006✔
329	if (!p) {	11,006✔
330	return NULL;	1,072✔
331	}
332
333	while (p >= haystack) {	455,594✔
334	if (u32_strncmp(p, needle, needle_len) == 0) {	449,746✔
335	return p;	4,086✔
336	}
337	--p;	445,660✔
338	}
339
340	return NULL;	5,848✔
341	}	5,553✔
342
343
344
345	void u32_insert_space_at(uint32_t **s, const size_t idx, const size_t n)	8✔
346	{
347	if (s == NULL \|\| n == 0) {	8✔
348	return;	4✔
349	}
350
351	size_t len = u32_strlen(*s);	4✔
352	size_t x = idx;	4✔
353	if (idx > len) {	4✔
354	x = len;	2✔
355	}	1✔
356
357	s = (uint32_t ) realloc(s, (len + 1 + n) sizeof(uint32_t));	4✔
358	u32_move(s + x + n, s + x, len - x);	4✔
359	u32_set(*s + x, char_space, n);	4✔
360	}	4✔
361
362
363	/* vim: set cindent sw=4: */

ascii-boxes / boxes / 7314850954

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous