6518013212

Committed 14 Oct 2023 01:37PM UTC coverage: 81.211% (-0.4%) from 81.608%

Build # 6518013212

Build Type

push

github

Committed by

tsjensen

Commit Message

remove

Run Details

2349 of 3210 branches covered (0.0%)

Branch coverage included in aggregate %.

1 of 1 new or added line in 1 file covered. (100.0%)

3767 of 4321 relevant lines covered (87.18%)

7801.63 hits per line

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

76.05

/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 *advance32(uint32_t *s, const size_t offset)
{
    if (is_empty(s)) {
        return new_empty_string32();
    }
    if (offset == 0) {
        return s;
    }

    size_t count = 0;                 /* the count of visible characters */
    int visible = 1;                  /* flag indicating whether the previous char was a visible char */
    const uint32_t *last_esc = NULL;  /* pointer to the start of the last escape sequence encountered */
    const uint32_t *rest = s;         /* pointer to the next character coming up */
    size_t step_invis = 0;            /* unused, but required for advance_next32() call */

    for (ucs4_t c = s[0]; c != char_nul; c = rest[0]) {
        if (c == char_esc) {
            last_esc = rest;
            visible = 0;
        } else {
            if (count++ == offset) {
                if (!visible && last_esc != NULL) {
                    return (uint32_t *) last_esc;
                }
                break;
            }
            visible = 1;
        }
        rest = advance_next32(rest, &step_invis);
    }
    return (uint32_t *) rest;         /* may point to zero terminator when offset too large */
}



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;
}


// TODO It seems skip is always 0, can we remove that parameter?
uint32_t *u32_strnrstr(const uint32_t *haystack, const uint32_t *needle, const size_t needle_len, int skip)
{
    if (is_empty(needle)) {
        return (uint32_t *) haystack;
    }
    if (is_empty(haystack)) {
        return NULL;
    }
    if (skip < 0) {
        skip = 0;
    }

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

    while (p >= haystack) {
        int comp = u32_strncmp(p, needle, needle_len);
        if (comp == 0) {
            if (skip--) {
                --p;
            }
            else {
                return p;
            }
        }
        else {
            --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)	618,037✔
60	{
61	return text != NULL && u32_cmp(text + idx, &expected_char, 1) == 0;	618,037!
62	}
63
64
65
66	void set_char_at(uint32_t *text, const size_t idx, const ucs4_t char_to_set)	38,844✔
67	{
68	u32_set(text + idx, char_to_set, 1);	38,844✔
69	}	38,844✔
70
71
72
73	int is_empty(const uint32_t *text)	617,611✔
74	{
75	return text == NULL \|\| is_char_at(text, 0, char_nul);	617,611✔
76	}
77
78
79
80	int u32_is_blank(const uint32_t *text)	1✔
81	{
82	if (is_empty(text)) {	1!
83	return 1;	×
84	}
85
86	for (const uint32_t c = text; c != char_nul; c++) {	5✔
87	if (!is_blank(*c)) {	4!
88	return 0;	×
89	}
90	}
91	return 1;	1✔
92	}
93
94
95
96	int is_ascii_printable(const ucs4_t c)	588,487✔
97	{
98	return c >= 0x20 && c < 0x7f;	588,487✔
99	}
100
101
102
103	int is_allowed_anywhere(const ucs4_t c)	712,657✔
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;	712,657✔
107	}
108
109
110
111	int is_allowed_in_shape(const ucs4_t c)	23,929✔
112	{
113	return is_allowed_anywhere(c) && c != char_cr && c != char_newline;	23,929✔
114	}
115
116
117
118	int is_allowed_in_sample(const ucs4_t c)	69,333✔
119	{
120	return is_allowed_anywhere(c);	69,333✔
121	}
122
123
124
125	int is_allowed_in_filename(const ucs4_t c)	246✔
126	{
127	return is_allowed_anywhere(c) && c != char_cr && c != char_newline && c != char_esc;	246✔
128	}
129
130
131
132	int is_allowed_in_kv_string(const ucs4_t c)	22,619✔
133	{
134	return is_allowed_anywhere(c) && c != char_cr && c != char_newline && c != char_esc;	22,619✔
135	}
136
137
138
139	int is_blank(const ucs4_t c)	1,179,770✔
140	{
141	return c == char_tab \|\| uc_is_blank(c);	1,179,770✔
142	}
143
144
145
146	uint32_t *new_empty_string32()	175✔
147	{
148	return (uint32_t *) calloc(1, sizeof(uint32_t));	175✔
149	}
150
151
152
153	ucs4_t to_utf32(char ascii)	1,057✔
154	{
155	ucs4_t c = char_nul;	1,057✔
156	if (ascii >= 0x20 && ascii < 0x7f) {	1,057!
157	char bytes = (char ) (&c);	1,056✔
158	bytes[0] = ascii;	1,056✔
159	}
160	return c;	1,057✔
161	}
162
163
164
165	uint32_t advance_next32(const uint32_t s, size_t *invis)	614,107✔
166	{
167	if (is_empty(s)) {	614,107!
168	return (uint32_t *) s;	×
169	}
170
171	int ansipos = 0;	614,107✔
172	(*invis) = 0;	614,107✔
173	ucs4_t c;
174	const uint32_t *rest = s;	614,107✔
175	while ((rest = u32_next(&c, rest))) {	676,234✔
176	if (ansipos == 0 && c == char_esc) {	676,233✔
177	/* Found an ESC char, count it as invisible and move 1 forward in the detection of CSI sequences */
178	(*invis)++;	9,994✔
179	ansipos++;	9,994✔
180	} else if (ansipos == 1 && (c == '[' \|\| c == '(')) {	666,239!
181	/* Found '[' char after ESC. A CSI sequence has started. */
182	(*invis)++;	9,994✔
183	ansipos++;	9,994✔
184	} else if (ansipos == 1 && c >= 0x40 && c <= 0x5f) { /* between '@' and '_' (mostly uppercase letters) */	656,245!
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) {	656,245✔
190	/* Inside CSI sequence - Keep counting chars as invisible */
191	(*invis)++;	52,132✔
192
193	/* A char between 0x40 and 0x7e signals the end of an CSI or escape sequence */
194	if (c >= 0x40 && c <= 0x7e) {	52,132!
195	ansipos = 0;	9,993✔
196	break;	9,993✔
197	}
198	} else {
199	break;	604,113✔
200	}
201	}
202	if (rest == NULL) {	614,107✔
203	rest = s + u32_strlen(s);	1✔
204	}
205	return (uint32_t *) rest;	614,107✔
206	}
207
208
209
210	uint32_t advance32(uint32_t s, const size_t offset)	×
211	{
212	if (is_empty(s)) {	×
213	return new_empty_string32();	×
214	}
215	if (offset == 0) {	×
216	return s;	×
217	}
218
219	size_t count = 0; /* the count of visible characters */	×
220	int visible = 1; /* flag indicating whether the previous char was a visible char */	×
221	const uint32_t last_esc = NULL; / pointer to the start of the last escape sequence encountered */	×
222	const uint32_t rest = s; / pointer to the next character coming up */	×
223	size_t step_invis = 0; /* unused, but required for advance_next32() call */	×
224
225	for (ucs4_t c = s[0]; c != char_nul; c = rest[0]) {	×
226	if (c == char_esc) {	×
227	last_esc = rest;	×
228	visible = 0;	×
229	} else {
230	if (count++ == offset) {	×
231	if (!visible && last_esc != NULL) {	×
232	return (uint32_t *) last_esc;	×
233	}
234	break;	×
235	}
236	visible = 1;	×
237	}
238	rest = advance_next32(rest, &step_invis);	×
239	}
240	return (uint32_t ) rest; / may point to zero terminator when offset too large */	×
241	}
242
243
244
245	uint32_t u32_strconv_from_input(const char src)	666✔
246	{
247	return u32_strconv_from_arg(src, encoding);	666✔
248	}
249
250
251
252	uint32_t u32_strconv_from_arg(const char src, const char *sourceEncoding)	17,969✔
253	{
254	if (src == NULL) {	17,969✔
255	return NULL;	2✔
256	}
257	if (src[0] == '\0') {	17,967✔
258	return new_empty_string32();	60✔
259	}
260
261	uint32_t *result = u32_strconv_from_encoding(	17,907✔
262	src, /* the source string to convert */
263	sourceEncoding, /* the character encoding from which to convert */
264	iconveh_question_mark); /* produce one question mark '?' per unconvertible character */
265
266	if (result == NULL) {	17,907!
267	fprintf(stderr, "%s: failed to convert from '%s' to UTF-32: %s\n", PROJECT, sourceEncoding, strerror(errno));	×
268	}
269	return result;	17,907✔
270	}
271
272
273
274	char u32_strconv_to_output(const uint32_t src)	1,283✔
275	{
276	return u32_strconv_to_arg(src, encoding);	1,283✔
277	}
278
279
280
281	char u32_strconv_to_arg(const uint32_t src, const char *targetEncoding)	1,447✔
282	{
283	if (src == NULL) {	1,447!
284	return NULL;	×
285	}
286	if (is_empty(src)) {	1,447!
287	return strdup("");	×
288	}
289
290	char *result = u32_strconv_to_encoding(	1,447✔
291	src, /* the source string to convert */
292	targetEncoding, /* the character encoding to which to convert */
293	iconveh_question_mark); /* produce one question mark '?' per unconvertible character */
294
295	if (result == NULL) {	1,447!
296	fprintf(stderr, "%s: failed to convert from UTF-32 to '%s': %s\n", PROJECT, targetEncoding, strerror(errno));	×
297	}
298	return result;	1,447✔
299	}
300
301
302
303	const char check_encoding(const char manual_encoding, const char *system_encoding)	160✔
304	{
305	if (manual_encoding != NULL) {	160✔
306	uint32_t *unicode = u32_strconv_from_encoding(" ", manual_encoding, iconveh_error);	13✔
307	if (unicode != NULL) {	13✔
308	BFREE(unicode);	12!
309	return manual_encoding;	12✔
310	}
311	fprintf(stderr, "%s: Invalid character encoding: %s - falling back to %s\n",	1✔
312	PROJECT, manual_encoding, system_encoding);
313	fflush(stderr);	1✔
314	}
315	return system_encoding;	148✔
316	}
317
318
319
320	char to_utf8(uint32_t src)	177✔
321	{
322	if (src == NULL) {	177!
323	return NULL;	×
324	}
325	if (is_empty(src)) {	177!
326	return (char *) strdup("");	×
327	}
328	char *result = u32_strconv_to_encoding(src, "UTF-8", iconveh_error);	177✔
329	if (result == NULL) {	177!
330	bx_fprintf(stderr, "%s: failed to convert a string to UTF-8: %s\n", PROJECT, strerror(errno));	×
331	return NULL;	×
332	}
333	return result;	177✔
334	}
335
336
337
338	uint32_t *u32_nspaces(const size_t n)	916✔
339	{
340	uint32_t result = (uint32_t ) malloc((n + 1) * sizeof(uint32_t));	916✔
341	if (result == NULL) {	916!
342	perror(PROJECT);	×
343	return NULL;	×
344	}
345	if (n > 0) {	916✔
346	u32_set(result, char_space, n);	716✔
347	}
348	set_char_at(result, n, char_nul);	916✔
349	return result;	916✔
350	}
351
352
353	// TODO It seems skip is always 0, can we remove that parameter?
354	uint32_t u32_strnrstr(const uint32_t haystack, const uint32_t *needle, const size_t needle_len, int skip)	344✔
355	{
356	if (is_empty(needle)) {	344✔
357	return (uint32_t *) haystack;	1✔
358	}
359	if (is_empty(haystack)) {	343✔
360	return NULL;	1✔
361	}
362	if (skip < 0) {	342✔
363	skip = 0;	1✔
364	}
365
366	uint32_t *p = u32_strrchr(haystack, needle[0]);	342✔
367	if (!p) {	342✔
368	return NULL;	2✔
369	}
370
371	while (p >= haystack) {	11,384✔
372	int comp = u32_strncmp(p, needle, needle_len);	11,137✔
373	if (comp == 0) {	11,137✔
374	if (skip--) {	94✔
375	--p;	1✔
376	}
377	else {
378	return p;	93✔
379	}
380	}
381	else {
382	--p;	11,043✔
383	}
384	}
385
386	return NULL;	247✔
387	}
388
389
390
391	void u32_insert_space_at(uint32_t **s, const size_t idx, const size_t n)	4✔
392	{
393	if (s == NULL \|\| n == 0) {	4✔
394	return;	2✔
395	}
396
397	size_t len = u32_strlen(*s);	2✔
398	size_t x = idx;	2✔
399	if (idx > len) {	2✔
400	x = len;	1✔
401	}
402
403	s = (uint32_t ) realloc(s, (len + 1 + n) sizeof(uint32_t));	2✔
404	u32_move(s + x + n, s + x, len - x);	2✔
405	u32_set(*s + x, char_space, n);	2✔
406	}
407
408
409	/* vim: set cindent sw=4: */

ascii-boxes / boxes / 6518013212

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