From: Junio C Hamano Date: Fri, 26 Feb 2016 21:37:23 +0000 (-0800) Subject: Merge branch 'tb/conversion' X-Git-Tag: v2.8.0-rc0~11 X-Git-Url: https://git.lorimer.id.au/gitweb.git/diff_plain/c6b94eb0093216f7a02a8c7a350d1760478a52a1?ds=inline;hp=-c Merge branch 'tb/conversion' Code simplification. * tb/conversion: convert.c: correct attr_action() convert.c: simplify text_stat convert.c: refactor crlf_action convert.c: use text_eol_is_crlf() convert.c: remove input_crlf_action() convert.c: remove unused parameter 'path' t0027: add tests for get_stream_filter() --- c6b94eb0093216f7a02a8c7a350d1760478a52a1 diff --combined convert.c index 8cd6222a26,d8b1f17e44..f524b8d7f4 --- a/convert.c +++ b/convert.c @@@ -19,17 -19,19 +19,19 @@@ #define CONVERT_STAT_BITS_BIN 0x4 enum crlf_action { - CRLF_GUESS = -1, - CRLF_BINARY = 0, + CRLF_UNDEFINED, + CRLF_BINARY, CRLF_TEXT, - CRLF_INPUT, - CRLF_CRLF, - CRLF_AUTO + CRLF_TEXT_INPUT, + CRLF_TEXT_CRLF, + CRLF_AUTO, + CRLF_AUTO_INPUT, + CRLF_AUTO_CRLF }; struct text_stat { /* NUL, CR, LF and CRLF counts */ - unsigned nul, cr, lf, crlf; + unsigned nul, lonecr, lonelf, crlf; /* These are just approximations! */ unsigned printable, nonprintable; @@@ -44,13 -46,15 +46,15 @@@ static void gather_stats(const char *bu for (i = 0; i < size; i++) { unsigned char c = buf[i]; if (c == '\r') { - stats->cr++; - if (i+1 < size && buf[i+1] == '\n') + if (i+1 < size && buf[i+1] == '\n') { stats->crlf++; + i++; + } else + stats->lonecr++; continue; } if (c == '\n') { - stats->lf++; + stats->lonelf++; continue; } if (c == 127) @@@ -84,7 -88,7 +88,7 @@@ */ static int convert_is_binary(unsigned long size, const struct text_stat *stats) { - if (stats->cr != stats->crlf) + if (stats->lonecr) return 1; if (stats->nul) return 1; @@@ -96,19 -100,18 +100,18 @@@ static unsigned int gather_convert_stats(const char *data, unsigned long size) { struct text_stat stats; + int ret = 0; if (!data || !size) return 0; gather_stats(data, size, &stats); if (convert_is_binary(size, &stats)) - return CONVERT_STAT_BITS_BIN; - else if (stats.crlf && stats.crlf == stats.lf) - return CONVERT_STAT_BITS_TXT_CRLF; - else if (stats.crlf && stats.lf) - return CONVERT_STAT_BITS_TXT_CRLF | CONVERT_STAT_BITS_TXT_LF; - else if (stats.lf) - return CONVERT_STAT_BITS_TXT_LF; - else - return 0; + ret |= CONVERT_STAT_BITS_BIN; + if (stats.crlf) + ret |= CONVERT_STAT_BITS_TXT_CRLF; + if (stats.lonelf) + ret |= CONVERT_STAT_BITS_TXT_LF; + + return ret; } static const char *gather_convert_stats_ascii(const char *data, unsigned long size) @@@ -149,28 -152,37 +152,37 @@@ const char *get_wt_convert_stats_ascii( return ret; } + static int text_eol_is_crlf(void) + { + if (auto_crlf == AUTO_CRLF_TRUE) + return 1; + else if (auto_crlf == AUTO_CRLF_INPUT) + return 0; + if (core_eol == EOL_CRLF) + return 1; + if (core_eol == EOL_UNSET && EOL_NATIVE == EOL_CRLF) + return 1; + return 0; + } + static enum eol output_eol(enum crlf_action crlf_action) { switch (crlf_action) { case CRLF_BINARY: return EOL_UNSET; - case CRLF_CRLF: + case CRLF_TEXT_CRLF: return EOL_CRLF; - case CRLF_INPUT: + case CRLF_TEXT_INPUT: return EOL_LF; - case CRLF_GUESS: - if (!auto_crlf) - return EOL_UNSET; - /* fall through */ + case CRLF_UNDEFINED: + case CRLF_AUTO_CRLF: + case CRLF_AUTO_INPUT: case CRLF_TEXT: case CRLF_AUTO: - if (auto_crlf == AUTO_CRLF_TRUE) - return EOL_CRLF; - else if (auto_crlf == AUTO_CRLF_INPUT) - return EOL_LF; - else if (core_eol == EOL_UNSET) - return EOL_NATIVE; + /* fall through */ + return text_eol_is_crlf() ? EOL_CRLF : EOL_LF; } + warning("Illegal crlf_action %d\n", (int)crlf_action); return core_eol; } @@@ -196,7 -208,7 +208,7 @@@ static void check_safe_crlf(const char * CRLFs would be added by checkout: * check if we have "naked" LFs */ - if (stats->lf != stats->crlf) { + if (stats->lonelf) { if (checksafe == SAFE_CRLF_WARN) warning("LF will be replaced by CRLF in %s.\nThe file will have its original line endings in your working directory.", path); else /* i.e. SAFE_CRLF_FAIL */ @@@ -227,7 -239,6 +239,6 @@@ static int crlf_to_git(const char *path char *dst; if (crlf_action == CRLF_BINARY || - (crlf_action == CRLF_GUESS && auto_crlf == AUTO_CRLF_FALSE) || (src && !len)) return 0; @@@ -240,11 -251,11 +251,11 @@@ gather_stats(src, len, &stats); - if (crlf_action == CRLF_AUTO || crlf_action == CRLF_GUESS) { + if (crlf_action == CRLF_AUTO || crlf_action == CRLF_AUTO_INPUT || crlf_action == CRLF_AUTO_CRLF) { if (convert_is_binary(len, &stats)) return 0; - if (crlf_action == CRLF_GUESS) { + if (crlf_action == CRLF_AUTO_INPUT || crlf_action == CRLF_AUTO_CRLF) { /* * If the file in the index has any CR in it, do not convert. * This is the new safer autocrlf handling. @@@ -256,8 -267,8 +267,8 @@@ check_safe_crlf(path, crlf_action, &stats, checksafe); - /* Optimization: No CR? Nothing to convert, regardless. */ - if (!stats.cr) + /* Optimization: No CRLF? Nothing to convert, regardless. */ + if (!stats.crlf) return 0; /* @@@ -271,7 -282,7 +282,7 @@@ if (strbuf_avail(buf) + buf->len < len) strbuf_grow(buf, len - buf->len); dst = buf->buf; - if (crlf_action == CRLF_AUTO || crlf_action == CRLF_GUESS) { + if (crlf_action == CRLF_AUTO || crlf_action == CRLF_AUTO_INPUT || crlf_action == CRLF_AUTO_CRLF) { /* * If we guessed, we already know we rejected a file with * lone CR, and we can strip a CR without looking at what @@@ -304,19 -315,15 +315,15 @@@ static int crlf_to_worktree(const char gather_stats(src, len, &stats); - /* No LF? Nothing to convert, regardless. */ - if (!stats.lf) - return 0; - - /* Was it already in CRLF format? */ - if (stats.lf == stats.crlf) + /* No "naked" LF? Nothing to convert, regardless. */ + if (!stats.lonelf) return 0; - if (crlf_action == CRLF_AUTO || crlf_action == CRLF_GUESS) { - if (crlf_action == CRLF_GUESS) { + if (crlf_action == CRLF_AUTO || crlf_action == CRLF_AUTO_INPUT || crlf_action == CRLF_AUTO_CRLF) { + if (crlf_action == CRLF_AUTO_INPUT || crlf_action == CRLF_AUTO_CRLF) { /* If we have any CR or CRLF line endings, we do not touch it */ /* This is the new safer autocrlf-handling */ - if (stats.cr > 0 || stats.crlf > 0) + if (stats.lonecr || stats.crlf ) return 0; } @@@ -328,7 -335,7 +335,7 @@@ if (src == buf->buf) to_free = strbuf_detach(buf, NULL); - strbuf_grow(buf, len + stats.lf - stats.crlf); + strbuf_grow(buf, len + stats.lonelf); for (;;) { const char *nl = memchr(src, '\n', len); if (!nl) @@@ -434,7 -441,7 +441,7 @@@ static int apply_filter(const char *pat struct async async; struct filter_params params; - if (!cmd) + if (!cmd || !*cmd) return 0; if (!dst) @@@ -696,7 -703,7 +703,7 @@@ static int ident_to_worktree(const cha return 1; } - static enum crlf_action git_path_check_crlf(const char *path, struct git_attr_check *check) + static enum crlf_action git_path_check_crlf(struct git_attr_check *check) { const char *value = check->value; @@@ -707,13 -714,13 +714,13 @@@ else if (ATTR_UNSET(value)) ; else if (!strcmp(value, "input")) - return CRLF_INPUT; + return CRLF_TEXT_INPUT; else if (!strcmp(value, "auto")) return CRLF_AUTO; - return CRLF_GUESS; + return CRLF_UNDEFINED; } - static enum eol git_path_check_eol(const char *path, struct git_attr_check *check) + static enum eol git_path_check_eol(struct git_attr_check *check) { const char *value = check->value; @@@ -726,8 -733,7 +733,7 @@@ return EOL_UNSET; } - static struct convert_driver *git_path_check_convert(const char *path, - struct git_attr_check *check) + static struct convert_driver *git_path_check_convert(struct git_attr_check *check) { const char *value = check->value; struct convert_driver *drv; @@@ -740,28 -746,17 +746,17 @@@ return NULL; } - static int git_path_check_ident(const char *path, struct git_attr_check *check) + static int git_path_check_ident(struct git_attr_check *check) { const char *value = check->value; return !!ATTR_TRUE(value); } - static enum crlf_action input_crlf_action(enum crlf_action text_attr, enum eol eol_attr) - { - if (text_attr == CRLF_BINARY) - return CRLF_BINARY; - if (eol_attr == EOL_LF) - return CRLF_INPUT; - if (eol_attr == EOL_CRLF) - return CRLF_CRLF; - return text_attr; - } - struct conv_attrs { struct convert_driver *drv; - enum crlf_action crlf_action; - enum eol eol_attr; + enum crlf_action attr_action; /* What attr says */ + enum crlf_action crlf_action; /* When no attr is set, use core.autocrlf */ int ident; }; @@@ -783,18 -778,33 +778,33 @@@ static void convert_attrs(struct conv_a } if (!git_check_attr(path, NUM_CONV_ATTRS, ccheck)) { - ca->crlf_action = git_path_check_crlf(path, ccheck + 4); - if (ca->crlf_action == CRLF_GUESS) - ca->crlf_action = git_path_check_crlf(path, ccheck + 0); - ca->ident = git_path_check_ident(path, ccheck + 1); - ca->drv = git_path_check_convert(path, ccheck + 2); - ca->eol_attr = git_path_check_eol(path, ccheck + 3); + ca->crlf_action = git_path_check_crlf(ccheck + 4); + if (ca->crlf_action == CRLF_UNDEFINED) + ca->crlf_action = git_path_check_crlf(ccheck + 0); + ca->attr_action = ca->crlf_action; + ca->ident = git_path_check_ident(ccheck + 1); + ca->drv = git_path_check_convert(ccheck + 2); + if (ca->crlf_action != CRLF_BINARY) { + enum eol eol_attr = git_path_check_eol(ccheck + 3); + if (eol_attr == EOL_LF) + ca->crlf_action = CRLF_TEXT_INPUT; + else if (eol_attr == EOL_CRLF) + ca->crlf_action = CRLF_TEXT_CRLF; + } + ca->attr_action = ca->crlf_action; } else { ca->drv = NULL; - ca->crlf_action = CRLF_GUESS; - ca->eol_attr = EOL_UNSET; + ca->crlf_action = CRLF_UNDEFINED; ca->ident = 0; } + if (ca->crlf_action == CRLF_TEXT) + ca->crlf_action = text_eol_is_crlf() ? CRLF_TEXT_CRLF : CRLF_TEXT_INPUT; + if (ca->crlf_action == CRLF_UNDEFINED && auto_crlf == AUTO_CRLF_FALSE) + ca->crlf_action = CRLF_BINARY; + if (ca->crlf_action == CRLF_UNDEFINED && auto_crlf == AUTO_CRLF_TRUE) + ca->crlf_action = CRLF_AUTO_CRLF; + if (ca->crlf_action == CRLF_UNDEFINED && auto_crlf == AUTO_CRLF_INPUT) + ca->crlf_action = CRLF_AUTO_INPUT; } int would_convert_to_git_filter_fd(const char *path) @@@ -819,23 -829,25 +829,25 @@@ const char *get_convert_attr_ascii(const char *path) { struct conv_attrs ca; - enum crlf_action crlf_action; convert_attrs(&ca, path); - crlf_action = input_crlf_action(ca.crlf_action, ca.eol_attr); - switch (crlf_action) { - case CRLF_GUESS: + switch (ca.attr_action) { + case CRLF_UNDEFINED: return ""; case CRLF_BINARY: return "-text"; case CRLF_TEXT: return "text"; - case CRLF_INPUT: + case CRLF_TEXT_INPUT: return "text eol=lf"; - case CRLF_CRLF: - return "text=auto eol=crlf"; + case CRLF_TEXT_CRLF: + return "text eol=crlf"; case CRLF_AUTO: return "text=auto"; + case CRLF_AUTO_CRLF: + return "text=auto eol=crlf"; /* This is not supported yet */ + case CRLF_AUTO_INPUT: + return "text=auto eol=lf"; /* This is not supported yet */ } return ""; } @@@ -862,7 -874,6 +874,6 @@@ int convert_to_git(const char *path, co src = dst->buf; len = dst->len; } - ca.crlf_action = input_crlf_action(ca.crlf_action, ca.eol_attr); ret |= crlf_to_git(path, src, len, dst, ca.crlf_action, checksafe); if (ret && dst) { src = dst->buf; @@@ -883,7 -894,6 +894,6 @@@ void convert_to_git_filter_fd(const cha if (!apply_filter(path, NULL, 0, fd, dst, ca.drv->clean)) die("%s: clean filter '%s' failed", path, ca.drv->name); - ca.crlf_action = input_crlf_action(ca.crlf_action, ca.eol_attr); crlf_to_git(path, dst->buf, dst->len, dst, ca.crlf_action, checksafe); ident_to_git(path, dst->buf, dst->len, dst, ca.ident); } @@@ -913,7 -923,6 +923,6 @@@ static int convert_to_working_tree_inte * is a smudge filter. The filter might expect CRLFs. */ if (filter || !normalizing) { - ca.crlf_action = input_crlf_action(ca.crlf_action, ca.eol_attr); ret |= crlf_to_worktree(path, src, len, dst, ca.crlf_action); if (ret) { src = dst->buf; @@@ -1382,14 -1391,15 +1391,15 @@@ struct stream_filter *get_stream_filter if (ca.ident) filter = ident_filter(sha1); - crlf_action = input_crlf_action(ca.crlf_action, ca.eol_attr); + crlf_action = ca.crlf_action; - if ((crlf_action == CRLF_BINARY) || (crlf_action == CRLF_INPUT) || - (crlf_action == CRLF_GUESS && auto_crlf == AUTO_CRLF_FALSE)) + if ((crlf_action == CRLF_BINARY) || + crlf_action == CRLF_AUTO_INPUT || + (crlf_action == CRLF_TEXT_INPUT)) filter = cascade_filter(filter, &null_filter_singleton); else if (output_eol(crlf_action) == EOL_CRLF && - !(crlf_action == CRLF_AUTO || crlf_action == CRLF_GUESS)) + !(crlf_action == CRLF_AUTO || crlf_action == CRLF_AUTO_CRLF)) filter = cascade_filter(filter, lf_to_crlf_filter()); return filter;