1779

Committed 16 Apr 2026 02:51PM UTC coverage: 85.037% (+1.7%) from 83.31%

Build # 1779

Build Type

push

travis-ci

Committed by

thoni56

Commit Message

[snapshot][version] Ignore snapshots with mismatching version, they will be recreated

Coverage Stats

16282 of 19147 relevant lines covered (85.04%)

15994227.93 hits per line

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

74.29

src/encoding.c

#include "encoding.h"

#include "options.h"


#define EDITOR_ENCODING_WALK_THROUGH_BUFFER(buffer, command) {          \
        unsigned char *s, *d, *max;                                     \
        unsigned char *text = (unsigned char *)getTextInEditorBuffer(buffer); \
        max = text + getSizeOfEditorBuffer(buffer);                     \
        for (s=d=text; s<max; s++) {                                    \
            command;                                                    \
            d++;                                                        \
        }                                                               \
        setSizeOfEditorBuffer(buffer, d - text);                        \
    }

#define EDITOR_ENCODING_CR_LF_OR_CR_TO_LF_CONVERSION(s,d)   \
    if (*s == '\r') {                                       \
        if (s+1<max && *(s+1)=='\n') {                      \
            s++;                                            \
            *d = *s;                                        \
        } else {                                            \
            *d = '\n';                                      \
        }                                                   \
    }
#define EDITOR_ENCODING_CR_LF_TO_LF_CONVERSION(s,d) \
    if (*s == '\r' && s+1<max && *(s+1)=='\n') {    \
        s++;                                        \
        *d = *s;                                    \
    }
#define EDITOR_ENCODING_CR_TO_LF_CONVERSION(s,d)      \
    if (*s == '\r') {                                 \
        *d = '\n';                                    \
    }

static bool convertUtf8(unsigned char **srcP, unsigned char **dstP) {
    if (**(srcP)&0x80) {
        unsigned z = **srcP;
        if (z >= 0xC2 && z <= 0xDF) {
            *srcP += 1;  // 2-byte sequence (U+0080 - U+07FF)
        } else if (z >= 0xE0 && z <= 0xEF) {
            *srcP += 2;  // 3-byte sequence (U+0800 - U+FFFF)
        } else if (z >= 0xF0 && z <= 0xF4) {
            *srcP += 3;  // 4-byte sequence (U+10000 - U+10FFFF)
        } else {
            // Illegal UTF-8, just skip one byte for minimal damage
            *srcP += 1;
        }

        **dstP = ' '; // Replace the sequence with a single space
        return true;
    }
    return false;
}


static void applyUtf8CrLfCrConversion(EditorBuffer *buffer) {
    EDITOR_ENCODING_WALK_THROUGH_BUFFER(buffer, {
            if (convertUtf8(&s, &d)) ;
            else EDITOR_ENCODING_CR_LF_OR_CR_TO_LF_CONVERSION(s,d)
                else
                    *d = *s;
        });
}

static void applyUtf8CrLfConversion(EditorBuffer *buffer) {
    EDITOR_ENCODING_WALK_THROUGH_BUFFER(buffer, {
            if (convertUtf8(&s, &d)) ;
            else EDITOR_ENCODING_CR_LF_TO_LF_CONVERSION(s,d)
                else
                    *d = *s;
        });
}

static void applyUtf8CrConversion(EditorBuffer *buffer) {
    EDITOR_ENCODING_WALK_THROUGH_BUFFER(buffer, {
            if (convertUtf8(&s, &d)) ;
            else EDITOR_ENCODING_CR_TO_LF_CONVERSION(s,d)
                else
                    *d = *s;
        });
}

static void applyUtf8Conversion(EditorBuffer *buffer) {
    EDITOR_ENCODING_WALK_THROUGH_BUFFER(buffer, {
            if (convertUtf8(&s, &d)) ;
            else
                *d = *s;
                });
}


void performEncodingAdjustments(EditorBuffer *buffer) {
    // utf-8
    if ((options.eolConversion&CR_LF_EOL_CONVERSION)
        && (options.eolConversion & CR_EOL_CONVERSION)) {
        applyUtf8CrLfCrConversion(buffer);
    } else if (options.eolConversion & CR_LF_EOL_CONVERSION) {
        applyUtf8CrLfConversion(buffer);
    } else if (options.eolConversion & CR_EOL_CONVERSION) {
        applyUtf8CrConversion(buffer);
    } else {
        applyUtf8Conversion(buffer);
    }
}

1	#include "encoding.h"
2
3	#include "options.h"
4
5
6	#define EDITOR_ENCODING_WALK_THROUGH_BUFFER(buffer, command) { \
7	unsigned char s, d, *max; \
8	unsigned char text = (unsigned char )getTextInEditorBuffer(buffer); \
9	max = text + getSizeOfEditorBuffer(buffer); \
10	for (s=d=text; s<max; s++) { \
11	command; \
12	d++; \
13	} \
14	setSizeOfEditorBuffer(buffer, d - text); \
15	}
16
17	#define EDITOR_ENCODING_CR_LF_OR_CR_TO_LF_CONVERSION(s,d) \
18	if (*s == '\r') { \
19	if (s+1<max && *(s+1)=='\n') { \
20	s++; \
21	d = s; \
22	} else { \
23	*d = '\n'; \
24	} \
25	}
26	#define EDITOR_ENCODING_CR_LF_TO_LF_CONVERSION(s,d) \
27	if (s == '\r' && s+1<max && (s+1)=='\n') { \
28	s++; \
29	d = s; \
30	}
31	#define EDITOR_ENCODING_CR_TO_LF_CONVERSION(s,d) \
32	if (*s == '\r') { \
33	*d = '\n'; \
34	}
35
36	static bool convertUtf8(unsigned char srcP, unsigned char dstP) {	2,147,483,647✔
37	if (**(srcP)&0x80) {	2,147,483,647✔
38	unsigned z = **srcP;	16,109✔
39	if (z >= 0xC2 && z <= 0xDF) {	16,109✔
40	*srcP += 1; // 2-byte sequence (U+0080 - U+07FF)	9,530✔
41	} else if (z >= 0xE0 && z <= 0xEF) {	6,579✔
42	*srcP += 2; // 3-byte sequence (U+0800 - U+FFFF)	6,491✔
43	} else if (z >= 0xF0 && z <= 0xF4) {	88✔
44	*srcP += 3; // 4-byte sequence (U+10000 - U+10FFFF)	88✔
45	} else {
46	// Illegal UTF-8, just skip one byte for minimal damage
47	*srcP += 1;	×
48	}
49
50	**dstP = ' '; // Replace the sequence with a single space	16,109✔
51	return true;	16,109✔
52	}
53	return false;
54	}
55
56
57	static void applyUtf8CrLfCrConversion(EditorBuffer *buffer) {	825✔
58	EDITOR_ENCODING_WALK_THROUGH_BUFFER(buffer, {
59	if (convertUtf8(&s, &d)) ;
60	else EDITOR_ENCODING_CR_LF_OR_CR_TO_LF_CONVERSION(s,d)
61	else
62	d = s;	825✔
63	});	825✔
64	}
65		×
66	static void applyUtf8CrLfConversion(EditorBuffer *buffer) {	×
67	EDITOR_ENCODING_WALK_THROUGH_BUFFER(buffer, {
68	if (convertUtf8(&s, &d)) ;
69	else EDITOR_ENCODING_CR_LF_TO_LF_CONVERSION(s,d)
70	else
71	d = s;	×
72	});
73	}
74		×
75	static void applyUtf8CrConversion(EditorBuffer *buffer) {	×
76	EDITOR_ENCODING_WALK_THROUGH_BUFFER(buffer, {
77	if (convertUtf8(&s, &d)) ;
78	else EDITOR_ENCODING_CR_TO_LF_CONVERSION(s,d)
79	else
80	d = s;	×
81	});
82	}
83		461,221✔
84	static void applyUtf8Conversion(EditorBuffer *buffer) {	2,147,483,647✔
85	EDITOR_ENCODING_WALK_THROUGH_BUFFER(buffer, {
86	if (convertUtf8(&s, &d)) ;
87	else
88	d = s;	461,221✔
89	});	461,221✔
90	}
91
92		462,046✔
93	void performEncodingAdjustments(EditorBuffer *buffer) {
94	// utf-8	462,046✔
95	if ((options.eolConversion&CR_LF_EOL_CONVERSION)	462,046✔
96	&& (options.eolConversion & CR_EOL_CONVERSION)) {	825✔
97	applyUtf8CrLfCrConversion(buffer);	461,221✔
98	} else if (options.eolConversion & CR_LF_EOL_CONVERSION) {	×
99	applyUtf8CrLfConversion(buffer);	461,221✔
100	} else if (options.eolConversion & CR_EOL_CONVERSION) {	×
101	applyUtf8CrConversion(buffer);
102	} else {	461,221✔
103	applyUtf8Conversion(buffer);
104	}	462,046✔
105	}

thoni56 / c-xrefactory / 1779

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