convert.c: refactor crlf_action
Refactor the determination and usage of crlf_action. Today, when no "crlf" attribute are set on a file, crlf_action is set to CRLF_GUESS. Use CRLF_UNDEFINED instead, and search for "text" or "eol" as before. After searching for line ending attributes, save the value in struct conv_attrs.crlf_action attr_action, so that get_convert_attr_ascii() is able report the attributes. Replace the old CRLF_GUESS usage: CRLF_GUESS && core.autocrlf=true -> CRLF_AUTO_CRLF CRLF_GUESS && core.autocrlf=false -> CRLF_BINARY CRLF_GUESS && core.autocrlf=input -> CRLF_AUTO_INPUT Save the action in conv_attrs.crlf_action (as before) and change all callers. Make more clear, what is what, by defining: - CRLF_UNDEFINED : No attributes set. Temparally used, until core.autocrlf and core.eol is evaluated and one of CRLF_BINARY, CRLF_AUTO_INPUT or CRLF_AUTO_CRLF is selected - CRLF_BINARY : No processing of line endings. - CRLF_TEXT : attribute "text" is set, line endings are processed. - CRLF_TEXT_INPUT: attribute "input" or "eol=lf" is set. This implies text. - CRLF_TEXT_CRLF : attribute "eol=crlf" is set. This implies text. - CRLF_AUTO : attribute "auto" is set. - CRLF_AUTO_INPUT: core.autocrlf=input (no attributes) - CRLF_AUTO_CRLF : core.autocrlf=true (no attributes) Signed-off-by: Torsten Bögershausen <tboegi@web.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Torsten Bögershausen committed
Feb 10, 2016 at 17:24 UTC
df747b818f0c9b7d0db1d7e3837b78e5d48b6fde
1 file changed
+46
-31
convert.c
+46
-31
@@ -19,12 +19,14 @@
19
#define CONVERT_STAT_BITS_BIN 0x4
20
21
enum crlf_action {
22
- CRLF_GUESS = -1,
23
- CRLF_BINARY = 0,
22
+ CRLF_UNDEFINED,
23
+ CRLF_BINARY,
24
CRLF_TEXT,
25
- CRLF_INPUT,
26
- CRLF_CRLF,
27
- CRLF_AUTO
25
+ CRLF_TEXT_INPUT,
26
+ CRLF_TEXT_CRLF,
27
+ CRLF_AUTO,
28
+ CRLF_AUTO_INPUT,
29
+ CRLF_AUTO_CRLF
30
};
31
32
struct text_stat {
@@ -167,18 +169,19 @@ static enum eol output_eol(enum crlf_action crlf_action)
169
switch (crlf_action) {
170
case CRLF_BINARY:
171
return EOL_UNSET;
170
- case CRLF_CRLF:
172
+ case CRLF_TEXT_CRLF:
173
return EOL_CRLF;
172
- case CRLF_INPUT:
174
+ case CRLF_TEXT_INPUT:
175
return EOL_LF;
174
- case CRLF_GUESS:
175
- if (!auto_crlf)
176
- return EOL_UNSET;
177
- /* fall through */
176
+ case CRLF_UNDEFINED:
177
+ case CRLF_AUTO_CRLF:
178
+ case CRLF_AUTO_INPUT:
179
case CRLF_TEXT:
180
case CRLF_AUTO:
181
+ /* fall through */
182
return text_eol_is_crlf() ? EOL_CRLF : EOL_LF;
183
}
184
+ warning("Illegal crlf_action %d\n", (int)crlf_action);
185
return core_eol;
186
}
187
@@ -235,7 +238,6 @@ static int crlf_to_git(const char *path, const char *src, size_t len,
238
char *dst;
239
240
if (crlf_action == CRLF_BINARY ||
238
- (crlf_action == CRLF_GUESS && auto_crlf == AUTO_CRLF_FALSE) ||
241
(src && !len))
242
return 0;
243
@@ -248,11 +250,11 @@ static int crlf_to_git(const char *path, const char *src, size_t len,
250
251
gather_stats(src, len, &stats);
252
251
- if (crlf_action == CRLF_AUTO || crlf_action == CRLF_GUESS) {
253
+ if (crlf_action == CRLF_AUTO || crlf_action == CRLF_AUTO_INPUT || crlf_action == CRLF_AUTO_CRLF) {
254
if (convert_is_binary(len, &stats))
255
return 0;
256
255
- if (crlf_action == CRLF_GUESS) {
257
+ if (crlf_action == CRLF_AUTO_INPUT || crlf_action == CRLF_AUTO_CRLF) {
258
/*
259
* If the file in the index has any CR in it, do not convert.
260
* This is the new safer autocrlf handling.
@@ -279,7 +281,7 @@ static int crlf_to_git(const char *path, const char *src, size_t len,
281
if (strbuf_avail(buf) + buf->len < len)
282
strbuf_grow(buf, len - buf->len);
283
dst = buf->buf;
282
- if (crlf_action == CRLF_AUTO || crlf_action == CRLF_GUESS) {
284
+ if (crlf_action == CRLF_AUTO || crlf_action == CRLF_AUTO_INPUT || crlf_action == CRLF_AUTO_CRLF) {
285
/*
286
* If we guessed, we already know we rejected a file with
287
* lone CR, and we can strip a CR without looking at what
@@ -320,8 +322,8 @@ static int crlf_to_worktree(const char *path, const char *src, size_t len,
322
if (stats.lf == stats.crlf)
323
return 0;
324
323
- if (crlf_action == CRLF_AUTO || crlf_action == CRLF_GUESS) {
324
- if (crlf_action == CRLF_GUESS) {
325
+ if (crlf_action == CRLF_AUTO || crlf_action == CRLF_AUTO_INPUT || crlf_action == CRLF_AUTO_CRLF) {
326
+ if (crlf_action == CRLF_AUTO_INPUT || crlf_action == CRLF_AUTO_CRLF) {
327
/* If we have any CR or CRLF line endings, we do not touch it */
328
/* This is the new safer autocrlf-handling */
329
if (stats.cr > 0 || stats.crlf > 0)
@@ -709,16 +711,16 @@ static enum crlf_action git_path_check_crlf(struct git_attr_check *check)
711
const char *value = check->value;
712
713
if (ATTR_TRUE(value))
712
- return CRLF_TEXT;
714
+ return text_eol_is_crlf() ? CRLF_TEXT_CRLF : CRLF_TEXT_INPUT;
715
else if (ATTR_FALSE(value))
716
return CRLF_BINARY;
717
else if (ATTR_UNSET(value))
718
;
719
else if (!strcmp(value, "input"))
718
- return CRLF_INPUT;
720
+ return CRLF_TEXT_INPUT;
721
else if (!strcmp(value, "auto"))
722
return CRLF_AUTO;
721
- return CRLF_GUESS;
723
+ return CRLF_UNDEFINED;
724
}
725
726
static enum eol git_path_check_eol(struct git_attr_check *check)
@@ -781,7 +783,7 @@ static void convert_attrs(struct conv_attrs *ca, const char *path)
783
if (!git_check_attr(path, NUM_CONV_ATTRS, ccheck)) {
784
enum eol eol_attr;
785
ca->crlf_action = git_path_check_crlf(ccheck + 4);
784
- if (ca->crlf_action == CRLF_GUESS)
786
+ if (ca->crlf_action == CRLF_UNDEFINED)
787
ca->crlf_action = git_path_check_crlf(ccheck + 0);
788
ca->attr_action = ca->crlf_action;
789
ca->ident = git_path_check_ident(ccheck + 1);
@@ -790,14 +792,22 @@ static void convert_attrs(struct conv_attrs *ca, const char *path)
792
return;
793
eol_attr = git_path_check_eol(ccheck + 3);
794
if (eol_attr == EOL_LF)
793
- ca->crlf_action = CRLF_INPUT;
795
+ ca->crlf_action = CRLF_TEXT_INPUT;
796
else if (eol_attr == EOL_CRLF)
795
- ca->crlf_action = CRLF_CRLF;
797
+ ca->crlf_action = CRLF_TEXT_CRLF;
798
} else {
799
ca->drv = NULL;
798
- ca->crlf_action = CRLF_GUESS;
800
+ ca->crlf_action = CRLF_UNDEFINED;
801
ca->ident = 0;
802
}
803
+ if (ca->crlf_action == CRLF_TEXT)
804
+ ca->crlf_action = text_eol_is_crlf() ? CRLF_TEXT_CRLF : CRLF_TEXT_INPUT;
805
+ if (ca->crlf_action == CRLF_UNDEFINED && auto_crlf == AUTO_CRLF_FALSE)
806
+ ca->crlf_action = CRLF_BINARY;
807
+ if (ca->crlf_action == CRLF_UNDEFINED && auto_crlf == AUTO_CRLF_TRUE)
808
+ ca->crlf_action = CRLF_AUTO_CRLF;
809
+ if (ca->crlf_action == CRLF_UNDEFINED && auto_crlf == AUTO_CRLF_INPUT)
810
+ ca->crlf_action = CRLF_AUTO_INPUT;
811
}
812
813
int would_convert_to_git_filter_fd(const char *path)
@@ -825,18 +835,22 @@ const char *get_convert_attr_ascii(const char *path)
835
836
convert_attrs(&ca, path);
837
switch (ca.attr_action) {
828
- case CRLF_GUESS:
838
+ case CRLF_UNDEFINED:
839
return "";
840
case CRLF_BINARY:
841
return "-text";
842
case CRLF_TEXT:
843
return "text";
834
- case CRLF_INPUT:
844
+ case CRLF_TEXT_INPUT:
845
return "text eol=lf";
836
- case CRLF_CRLF:
837
- return "text=auto eol=crlf";
846
+ case CRLF_TEXT_CRLF:
847
+ return "text eol=crlf";
848
case CRLF_AUTO:
849
return "text=auto";
850
+ case CRLF_AUTO_CRLF:
851
+ return "text=auto eol=crlf"; /* This is not supported yet */
852
+ case CRLF_AUTO_INPUT:
853
+ return "text=auto eol=lf"; /* This is not supported yet */
854
}
855
return "";
856
}
@@ -1382,12 +1396,13 @@ struct stream_filter *get_stream_filter(const char *path, const unsigned char *s
1396
1397
crlf_action = ca.crlf_action;
1398
1385
- if ((crlf_action == CRLF_BINARY) || (crlf_action == CRLF_INPUT) ||
1386
- (crlf_action == CRLF_GUESS && auto_crlf == AUTO_CRLF_FALSE))
1399
+ if ((crlf_action == CRLF_BINARY) ||
1400
+ crlf_action == CRLF_AUTO_INPUT ||
1401
+ (crlf_action == CRLF_TEXT_INPUT))
1402
filter = cascade_filter(filter, &null_filter_singleton);
1403
1404
else if (output_eol(crlf_action) == EOL_CRLF &&
1390
- !(crlf_action == CRLF_AUTO || crlf_action == CRLF_GUESS))
1405
+ !(crlf_action == CRLF_AUTO || crlf_action == CRLF_AUTO_CRLF))
1406
filter = cascade_filter(filter, lf_to_crlf_filter());
1407
1408
return filter;