X-Git-Url: https://git.tokkee.org/?a=blobdiff_plain;f=convert.c;h=85939c29be67d4179a2afb9069b575afed4d8bb2;hb=9e37a7e126c98513789ce60c4bec67d7940dbf4b;hp=7eb51b16ed03e650f3af11383c5c43c00d7d9812;hpb=93446aa760041a5a6f55605d94cdfad7bcd5a2f1;p=git.git

diff --git a/convert.c b/convert.c
index 7eb51b16e..85939c29b 100644
--- a/convert.c
+++ b/convert.c
@@ -12,7 +12,7 @@
  * translation when the "text" attribute or "auto_crlf" option is set.
  */
 
-enum action {
+enum crlf_action {
 	CRLF_GUESS = -1,
 	CRLF_BINARY = 0,
 	CRLF_TEXT,
@@ -94,9 +94,9 @@ static int is_binary(unsigned long size, struct text_stat *stats)
 	return 0;
 }
 
-static enum eol determine_output_conversion(enum action action)
+static enum eol output_eol(enum crlf_action crlf_action)
 {
-	switch (action) {
+	switch (crlf_action) {
 	case CRLF_BINARY:
 		return EOL_UNSET;
 	case CRLF_CRLF:
@@ -113,19 +113,19 @@ static enum eol determine_output_conversion(enum action action)
 			return EOL_CRLF;
 		else if (auto_crlf == AUTO_CRLF_INPUT)
 			return EOL_LF;
-		else if (eol == EOL_UNSET)
+		else if (core_eol == EOL_UNSET)
 			return EOL_NATIVE;
 	}
-	return eol;
+	return core_eol;
 }
 
-static void check_safe_crlf(const char *path, enum action action,
+static void check_safe_crlf(const char *path, enum crlf_action crlf_action,
                             struct text_stat *stats, enum safe_crlf checksafe)
 {
 	if (!checksafe)
 		return;
 
-	if (determine_output_conversion(action) == EOL_LF) {
+	if (output_eol(crlf_action) == EOL_LF) {
 		/*
 		 * CRLFs would not be restored by checkout:
 		 * check if we'd remove CRLFs
@@ -136,7 +136,7 @@ static void check_safe_crlf(const char *path, enum action action,
 			else /* i.e. SAFE_CRLF_FAIL */
 				die("CRLF would be replaced by LF in %s.", path);
 		}
-	} else if (determine_output_conversion(action) == EOL_CRLF) {
+	} else if (output_eol(crlf_action) == EOL_CRLF) {
 		/*
 		 * CRLFs would be added by checkout:
 		 * check if we have "naked" LFs
@@ -188,18 +188,19 @@ static int has_cr_in_index(const char *path)
 }
 
 static int crlf_to_git(const char *path, const char *src, size_t len,
-		       struct strbuf *buf, enum action action, enum safe_crlf checksafe)
+		       struct strbuf *buf,
+		       enum crlf_action crlf_action, enum safe_crlf checksafe)
 {
 	struct text_stat stats;
 	char *dst;
 
-	if (action == CRLF_BINARY ||
-	    (action == CRLF_GUESS && auto_crlf == AUTO_CRLF_FALSE) || !len)
+	if (crlf_action == CRLF_BINARY ||
+	    (crlf_action == CRLF_GUESS && auto_crlf == AUTO_CRLF_FALSE) || !len)
 		return 0;
 
 	gather_stats(src, len, &stats);
 
-	if (action == CRLF_AUTO || action == CRLF_GUESS) {
+	if (crlf_action == CRLF_AUTO || crlf_action == CRLF_GUESS) {
 		/*
 		 * We're currently not going to even try to convert stuff
 		 * that has bare CR characters. Does anybody do that crazy
@@ -214,7 +215,7 @@ static int crlf_to_git(const char *path, const char *src, size_t len,
 		if (is_binary(len, &stats))
 			return 0;
 
-		if (action == CRLF_GUESS) {
+		if (crlf_action == CRLF_GUESS) {
 			/*
 			 * If the file in the index has any CR in it, do not convert.
 			 * This is the new safer autocrlf handling.
@@ -224,7 +225,7 @@ static int crlf_to_git(const char *path, const char *src, size_t len,
 		}
 	}
 
-	check_safe_crlf(path, action, &stats, checksafe);
+	check_safe_crlf(path, crlf_action, &stats, checksafe);
 
 	/* Optimization: No CR? Nothing to convert, regardless. */
 	if (!stats.cr)
@@ -234,7 +235,7 @@ static int crlf_to_git(const char *path, const char *src, size_t len,
 	if (strbuf_avail(buf) + buf->len < len)
 		strbuf_grow(buf, len - buf->len);
 	dst = buf->buf;
-	if (action == CRLF_AUTO || action == CRLF_GUESS) {
+	if (crlf_action == CRLF_AUTO || crlf_action == CRLF_GUESS) {
 		/*
 		 * If we guessed, we already know we rejected a file with
 		 * lone CR, and we can strip a CR without looking at what
@@ -257,12 +258,12 @@ static int crlf_to_git(const char *path, const char *src, size_t len,
 }
 
 static int crlf_to_worktree(const char *path, const char *src, size_t len,
-			    struct strbuf *buf, enum action action)
+			    struct strbuf *buf, enum crlf_action crlf_action)
 {
 	char *to_free = NULL;
 	struct text_stat stats;
 
-	if (!len || determine_output_conversion(action) != EOL_CRLF)
+	if (!len || output_eol(crlf_action) != EOL_CRLF)
 		return 0;
 
 	gather_stats(src, len, &stats);
@@ -275,8 +276,8 @@ static int crlf_to_worktree(const char *path, const char *src, size_t len,
 	if (stats.lf == stats.crlf)
 		return 0;
 
-	if (action == CRLF_AUTO || action == CRLF_GUESS) {
-		if (action == CRLF_GUESS) {
+	if (crlf_action == CRLF_AUTO || crlf_action == CRLF_GUESS) {
+		if (crlf_action == CRLF_GUESS) {
 			/* 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)
@@ -474,30 +475,6 @@ static int read_convert_config(const char *var, const char *value, void *cb)
 	return 0;
 }
 
-static void setup_convert_check(struct git_attr_check *check)
-{
-	static struct git_attr *attr_text;
-	static struct git_attr *attr_crlf;
-	static struct git_attr *attr_eol;
-	static struct git_attr *attr_ident;
-	static struct git_attr *attr_filter;
-
-	if (!attr_text) {
-		attr_text = git_attr("text");
-		attr_crlf = git_attr("crlf");
-		attr_eol = git_attr("eol");
-		attr_ident = git_attr("ident");
-		attr_filter = git_attr("filter");
-		user_convert_tail = &user_convert;
-		git_config(read_convert_config, NULL);
-	}
-	check[0].attr = attr_crlf;
-	check[1].attr = attr_ident;
-	check[2].attr = attr_filter;
-	check[3].attr = attr_eol;
-	check[4].attr = attr_text;
-}
-
 static int count_ident(const char *cp, unsigned long size)
 {
 	/*
@@ -715,7 +692,7 @@ static int git_path_check_ident(const char *path, struct git_attr_check *check)
 	return !!ATTR_TRUE(value);
 }
 
-static enum action determine_action(enum action text_attr, enum eol eol_attr)
+static enum crlf_action input_crlf_action(enum crlf_action text_attr, enum eol eol_attr)
 {
 	if (text_attr == CRLF_BINARY)
 		return CRLF_BINARY;
@@ -726,66 +703,83 @@ static enum action determine_action(enum action text_attr, enum eol eol_attr)
 	return text_attr;
 }
 
+struct conv_attrs {
+	struct convert_driver *drv;
+	enum crlf_action crlf_action;
+	enum eol eol_attr;
+	int ident;
+};
+
+static const char *conv_attr_name[] = {
+	"crlf", "ident", "filter", "eol", "text",
+};
+#define NUM_CONV_ATTRS ARRAY_SIZE(conv_attr_name)
+
+static void convert_attrs(struct conv_attrs *ca, const char *path)
+{
+	int i;
+	static struct git_attr_check ccheck[NUM_CONV_ATTRS];
+
+	if (!ccheck[0].attr) {
+		for (i = 0; i < NUM_CONV_ATTRS; i++)
+			ccheck[i].attr = git_attr(conv_attr_name[i]);
+		user_convert_tail = &user_convert;
+		git_config(read_convert_config, NULL);
+	}
+
+	if (!git_checkattr(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);
+	} else {
+		ca->drv = NULL;
+		ca->crlf_action = CRLF_GUESS;
+		ca->eol_attr = EOL_UNSET;
+		ca->ident = 0;
+	}
+}
+
 int convert_to_git(const char *path, const char *src, size_t len,
                    struct strbuf *dst, enum safe_crlf checksafe)
 {
-	struct git_attr_check check[5];
-	enum action action = CRLF_GUESS;
-	enum eol eol_attr = EOL_UNSET;
-	int ident = 0, ret = 0;
+	int ret = 0;
 	const char *filter = NULL;
+	struct conv_attrs ca;
 
-	setup_convert_check(check);
-	if (!git_checkattr(path, ARRAY_SIZE(check), check)) {
-		struct convert_driver *drv;
-		action = git_path_check_crlf(path, check + 4);
-		if (action == CRLF_GUESS)
-			action = git_path_check_crlf(path, check + 0);
-		ident = git_path_check_ident(path, check + 1);
-		drv = git_path_check_convert(path, check + 2);
-		eol_attr = git_path_check_eol(path, check + 3);
-		if (drv && drv->clean)
-			filter = drv->clean;
-	}
+	convert_attrs(&ca, path);
+	if (ca.drv)
+		filter = ca.drv->clean;
 
 	ret |= apply_filter(path, src, len, dst, filter);
 	if (ret) {
 		src = dst->buf;
 		len = dst->len;
 	}
-	action = determine_action(action, eol_attr);
-	ret |= crlf_to_git(path, src, len, dst, action, checksafe);
+	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) {
 		src = dst->buf;
 		len = dst->len;
 	}
-	return ret | ident_to_git(path, src, len, dst, ident);
+	return ret | ident_to_git(path, src, len, dst, ca.ident);
 }
 
 static int convert_to_working_tree_internal(const char *path, const char *src,
 					    size_t len, struct strbuf *dst,
 					    int normalizing)
 {
-	struct git_attr_check check[5];
-	enum action action = CRLF_GUESS;
-	enum eol eol_attr = EOL_UNSET;
-	int ident = 0, ret = 0;
+	int ret = 0;
 	const char *filter = NULL;
+	struct conv_attrs ca;
 
-	setup_convert_check(check);
-	if (!git_checkattr(path, ARRAY_SIZE(check), check)) {
-		struct convert_driver *drv;
-		action = git_path_check_crlf(path, check + 4);
-		if (action == CRLF_GUESS)
-			action = git_path_check_crlf(path, check + 0);
-		ident = git_path_check_ident(path, check + 1);
-		drv = git_path_check_convert(path, check + 2);
-		eol_attr = git_path_check_eol(path, check + 3);
-		if (drv && drv->smudge)
-			filter = drv->smudge;
-	}
+	convert_attrs(&ca, path);
+	if (ca.drv)
+		filter = ca.drv->smudge;
 
-	ret |= ident_to_worktree(path, src, len, dst, ident);
+	ret |= ident_to_worktree(path, src, len, dst, ca.ident);
 	if (ret) {
 		src = dst->buf;
 		len = dst->len;
@@ -795,8 +789,8 @@ static int convert_to_working_tree_internal(const char *path, const char *src,
 	 * is a smudge filter.  The filter might expect CRLFs.
 	 */
 	if (filter || !normalizing) {
-		action = determine_action(action, eol_attr);
-		ret |= crlf_to_worktree(path, src, len, dst, action);
+		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;
 			len = dst->len;
@@ -819,3 +813,400 @@ int renormalize_buffer(const char *path, const char *src, size_t len, struct str
 	}
 	return ret | convert_to_git(path, src, len, dst, 0);
 }
+
+/*****************************************************************
+ *
+ * Streaming converison support
+ *
+ *****************************************************************/
+
+typedef int (*filter_fn)(struct stream_filter *,
+			 const char *input, size_t *isize_p,
+			 char *output, size_t *osize_p);
+typedef void (*free_fn)(struct stream_filter *);
+
+struct stream_filter_vtbl {
+	filter_fn filter;
+	free_fn free;
+};
+
+struct stream_filter {
+	struct stream_filter_vtbl *vtbl;
+};
+
+static int null_filter_fn(struct stream_filter *filter,
+			  const char *input, size_t *isize_p,
+			  char *output, size_t *osize_p)
+{
+	size_t count;
+
+	if (!input)
+		return 0; /* we do not keep any states */
+	count = *isize_p;
+	if (*osize_p < count)
+		count = *osize_p;
+	if (count) {
+		memmove(output, input, count);
+		*isize_p -= count;
+		*osize_p -= count;
+	}
+	return 0;
+}
+
+static void null_free_fn(struct stream_filter *filter)
+{
+	; /* nothing -- null instances are shared */
+}
+
+static struct stream_filter_vtbl null_vtbl = {
+	null_filter_fn,
+	null_free_fn,
+};
+
+static struct stream_filter null_filter_singleton = {
+	&null_vtbl,
+};
+
+int is_null_stream_filter(struct stream_filter *filter)
+{
+	return filter == &null_filter_singleton;
+}
+
+
+/*
+ * LF-to-CRLF filter
+ */
+static int lf_to_crlf_filter_fn(struct stream_filter *filter,
+				const char *input, size_t *isize_p,
+				char *output, size_t *osize_p)
+{
+	size_t count;
+
+	if (!input)
+		return 0; /* we do not keep any states */
+	count = *isize_p;
+	if (count) {
+		size_t i, o;
+		for (i = o = 0; o < *osize_p && i < count; i++) {
+			char ch = input[i];
+			if (ch == '\n') {
+				if (o + 1 < *osize_p)
+					output[o++] = '\r';
+				else
+					break;
+			}
+			output[o++] = ch;
+		}
+
+		*osize_p -= o;
+		*isize_p -= i;
+	}
+	return 0;
+}
+
+static struct stream_filter_vtbl lf_to_crlf_vtbl = {
+	lf_to_crlf_filter_fn,
+	null_free_fn,
+};
+
+static struct stream_filter lf_to_crlf_filter_singleton = {
+	&lf_to_crlf_vtbl,
+};
+
+
+/*
+ * Cascade filter
+ */
+#define FILTER_BUFFER 1024
+struct cascade_filter {
+	struct stream_filter filter;
+	struct stream_filter *one;
+	struct stream_filter *two;
+	char buf[FILTER_BUFFER];
+	int end, ptr;
+};
+
+static int cascade_filter_fn(struct stream_filter *filter,
+			     const char *input, size_t *isize_p,
+			     char *output, size_t *osize_p)
+{
+	struct cascade_filter *cas = (struct cascade_filter *) filter;
+	size_t filled = 0;
+	size_t sz = *osize_p;
+	size_t to_feed, remaining;
+
+	/*
+	 * input -- (one) --> buf -- (two) --> output
+	 */
+	while (filled < sz) {
+		remaining = sz - filled;
+
+		/* do we already have something to feed two with? */
+		if (cas->ptr < cas->end) {
+			to_feed = cas->end - cas->ptr;
+			if (stream_filter(cas->two,
+					  cas->buf + cas->ptr, &to_feed,
+					  output + filled, &remaining))
+				return -1;
+			cas->ptr += (cas->end - cas->ptr) - to_feed;
+			filled = sz - remaining;
+			continue;
+		}
+
+		/* feed one from upstream and have it emit into our buffer */
+		to_feed = input ? *isize_p : 0;
+		if (input && !to_feed)
+			break;
+		remaining = sizeof(cas->buf);
+		if (stream_filter(cas->one,
+				  input, &to_feed,
+				  cas->buf, &remaining))
+			return -1;
+		cas->end = sizeof(cas->buf) - remaining;
+		cas->ptr = 0;
+		if (input) {
+			size_t fed = *isize_p - to_feed;
+			*isize_p -= fed;
+			input += fed;
+		}
+
+		/* do we know that we drained one completely? */
+		if (input || cas->end)
+			continue;
+
+		/* tell two to drain; we have nothing more to give it */
+		to_feed = 0;
+		remaining = sz - filled;
+		if (stream_filter(cas->two,
+				  NULL, &to_feed,
+				  output + filled, &remaining))
+			return -1;
+		if (remaining == (sz - filled))
+			break; /* completely drained two */
+		filled = sz - remaining;
+	}
+	*osize_p -= filled;
+	return 0;
+}
+
+static void cascade_free_fn(struct stream_filter *filter)
+{
+	struct cascade_filter *cas = (struct cascade_filter *)filter;
+	free_stream_filter(cas->one);
+	free_stream_filter(cas->two);
+	free(filter);
+}
+
+static struct stream_filter_vtbl cascade_vtbl = {
+	cascade_filter_fn,
+	cascade_free_fn,
+};
+
+static struct stream_filter *cascade_filter(struct stream_filter *one,
+					    struct stream_filter *two)
+{
+	struct cascade_filter *cascade;
+
+	if (!one || is_null_stream_filter(one))
+		return two;
+	if (!two || is_null_stream_filter(two))
+		return one;
+
+	cascade = xmalloc(sizeof(*cascade));
+	cascade->one = one;
+	cascade->two = two;
+	cascade->end = cascade->ptr = 0;
+	cascade->filter.vtbl = &cascade_vtbl;
+	return (struct stream_filter *)cascade;
+}
+
+/*
+ * ident filter
+ */
+#define IDENT_DRAINING (-1)
+#define IDENT_SKIPPING (-2)
+struct ident_filter {
+	struct stream_filter filter;
+	struct strbuf left;
+	int state;
+	char ident[45]; /* ": x40 $" */
+};
+
+static int is_foreign_ident(const char *str)
+{
+	int i;
+
+	if (prefixcmp(str, "$Id: "))
+		return 0;
+	for (i = 5; str[i]; i++) {
+		if (isspace(str[i]) && str[i+1] != '$')
+			return 1;
+	}
+	return 0;
+}
+
+static void ident_drain(struct ident_filter *ident, char **output_p, size_t *osize_p)
+{
+	size_t to_drain = ident->left.len;
+
+	if (*osize_p < to_drain)
+		to_drain = *osize_p;
+	if (to_drain) {
+		memcpy(*output_p, ident->left.buf, to_drain);
+		strbuf_remove(&ident->left, 0, to_drain);
+		*output_p += to_drain;
+		*osize_p -= to_drain;
+	}
+	if (!ident->left.len)
+		ident->state = 0;
+}
+
+static int ident_filter_fn(struct stream_filter *filter,
+			   const char *input, size_t *isize_p,
+			   char *output, size_t *osize_p)
+{
+	struct ident_filter *ident = (struct ident_filter *)filter;
+	static const char head[] = "$Id";
+
+	if (!input) {
+		/* drain upon eof */
+		switch (ident->state) {
+		default:
+			strbuf_add(&ident->left, head, ident->state);
+		case IDENT_SKIPPING:
+			/* fallthru */
+		case IDENT_DRAINING:
+			ident_drain(ident, &output, osize_p);
+		}
+		return 0;
+	}
+
+	while (*isize_p || (ident->state == IDENT_DRAINING)) {
+		int ch;
+
+		if (ident->state == IDENT_DRAINING) {
+			ident_drain(ident, &output, osize_p);
+			if (!*osize_p)
+				break;
+			continue;
+		}
+
+		ch = *(input++);
+		(*isize_p)--;
+
+		if (ident->state == IDENT_SKIPPING) {
+			/*
+			 * Skipping until '$' or LF, but keeping them
+			 * in case it is a foreign ident.
+			 */
+			strbuf_addch(&ident->left, ch);
+			if (ch != '\n' && ch != '$')
+				continue;
+			if (ch == '$' && !is_foreign_ident(ident->left.buf)) {
+				strbuf_setlen(&ident->left, sizeof(head) - 1);
+				strbuf_addstr(&ident->left, ident->ident);
+			}
+			ident->state = IDENT_DRAINING;
+			continue;
+		}
+
+		if (ident->state < sizeof(head) &&
+		    head[ident->state] == ch) {
+			ident->state++;
+			continue;
+		}
+
+		if (ident->state)
+			strbuf_add(&ident->left, head, ident->state);
+		if (ident->state == sizeof(head) - 1) {
+			if (ch != ':' && ch != '$') {
+				strbuf_addch(&ident->left, ch);
+				ident->state = 0;
+				continue;
+			}
+
+			if (ch == ':') {
+				strbuf_addch(&ident->left, ch);
+				ident->state = IDENT_SKIPPING;
+			} else {
+				strbuf_addstr(&ident->left, ident->ident);
+				ident->state = IDENT_DRAINING;
+			}
+			continue;
+		}
+
+		strbuf_addch(&ident->left, ch);
+		ident->state = IDENT_DRAINING;
+	}
+	return 0;
+}
+
+static void ident_free_fn(struct stream_filter *filter)
+{
+	struct ident_filter *ident = (struct ident_filter *)filter;
+	strbuf_release(&ident->left);
+	free(filter);
+}
+
+static struct stream_filter_vtbl ident_vtbl = {
+	ident_filter_fn,
+	ident_free_fn,
+};
+
+static struct stream_filter *ident_filter(const unsigned char *sha1)
+{
+	struct ident_filter *ident = xmalloc(sizeof(*ident));
+
+	sprintf(ident->ident, ": %s $", sha1_to_hex(sha1));
+	strbuf_init(&ident->left, 0);
+	ident->filter.vtbl = &ident_vtbl;
+	ident->state = 0;
+	return (struct stream_filter *)ident;
+}
+
+/*
+ * Return an appropriately constructed filter for the path, or NULL if
+ * the contents cannot be filtered without reading the whole thing
+ * in-core.
+ *
+ * Note that you would be crazy to set CRLF, smuge/clean or ident to a
+ * large binary blob you would want us not to slurp into the memory!
+ */
+struct stream_filter *get_stream_filter(const char *path, const unsigned char *sha1)
+{
+	struct conv_attrs ca;
+	enum crlf_action crlf_action;
+	struct stream_filter *filter = NULL;
+
+	convert_attrs(&ca, path);
+
+	if (ca.drv && (ca.drv->smudge || ca.drv->clean))
+		return filter;
+
+	if (ca.ident)
+		filter = ident_filter(sha1);
+
+	crlf_action = input_crlf_action(ca.crlf_action, ca.eol_attr);
+
+	if ((crlf_action == CRLF_BINARY) || (crlf_action == CRLF_INPUT) ||
+	    (crlf_action == CRLF_GUESS && auto_crlf == AUTO_CRLF_FALSE))
+		filter = cascade_filter(filter, &null_filter_singleton);
+
+	else if (output_eol(crlf_action) == EOL_CRLF &&
+		 !(crlf_action == CRLF_AUTO || crlf_action == CRLF_GUESS))
+		filter = cascade_filter(filter, &lf_to_crlf_filter_singleton);
+
+	return filter;
+}
+
+void free_stream_filter(struct stream_filter *filter)
+{
+	filter->vtbl->free(filter);
+}
+
+int stream_filter(struct stream_filter *filter,
+		  const char *input, size_t *isize_p,
+		  char *output, size_t *osize_p)
+{
+	return filter->vtbl->filter(filter, input, isize_p, output, osize_p);
+}