Add APIs for git attributes

This adds APIs for querying git attributes.  In addition to
the new API in include/git2/attr.h, most of the action is in
src/attr_file.[hc] which contains utilities for dealing with
a single attributes file, and src/attr.[hc] which contains
the implementation of the APIs that merge all applicable
attributes files.

1 files changed, 456 insertions, 0 deletions

diff --git a/src/attr_file.c b/src/attr_file.c
new file mode 100644
index 000000000..5d159db00
--- /dev/null
+++ b/src/attr_file.c
@@ -0,0 +1,456 @@
+#include "common.h"
+#include "attr_file.h"
+#include "filebuf.h"
+#include <ctype.h>
+
+const char *git_attr__true  = "[internal]__TRUE__";
+const char *git_attr__false = "[internal]__FALSE__";
+
+static int parse_fnmatch(git_attr_fnmatch *spec, const char **base);
+static int parse_assigns(git_vector *assigns, const char **base);
+static int free_rule(git_attr_rule *rule);
+static int sort_by_hash_and_name(const void *a_raw, const void *b_raw);
+
+int git_attr_file__from_buffer(git_attr_file **out, const char *buffer)
+{
+	int error = GIT_SUCCESS;
+	git_attr_file *attrs = NULL;
+	const char *scan = NULL;
+	git_attr_rule *rule = NULL;
+
+	*out = NULL;
+
+	attrs = git__calloc(1, sizeof(git_attr_file));
+	if (attrs == NULL)
+		return git__throw(GIT_ENOMEM, "Could not allocate attribute storage");
+
+	attrs->path = NULL;
+
+	error = git_vector_init(&attrs->rules, 4, NULL);
+	if (error != GIT_SUCCESS) {
+		git__rethrow(error, "Could not initialize attribute storage");
+		goto cleanup;
+	}
+
+	scan = buffer;
+
+	while (error == GIT_SUCCESS && *scan) {
+		/* allocate rule if needed */
+		if (!rule && !(rule = git__calloc(1, sizeof(git_attr_rule)))) {
+			error = GIT_ENOMEM;
+			break;
+		}
+
+		/* parse the next "pattern attr attr attr" line */
+		if (!(error = parse_fnmatch(&rule->match, &scan)) &&
+			!(error = parse_assigns(&rule->assigns, &scan)))
+			error = git_vector_insert(&attrs->rules, rule);
+
+		/* if the rule wasn't a pattern, on to the next */
+		if (error != GIT_SUCCESS) {
+			free_rule(rule); /* release anything partially allocated */
+			if (error == GIT_ENOTFOUND)
+				error = GIT_SUCCESS;
+		} else {
+			rule = NULL; /* vector now "owns" the rule */
+		}
+	}
+
+cleanup:
+	if (error != GIT_SUCCESS) {
+		git_attr_file__free(attrs);
+		git__free(attrs);
+	} else {
+		*out = attrs;
+	}
+
+	return error;
+}
+
+int git_attr_file__from_file(git_attr_file **out, const char *path)
+{
+	int error = GIT_SUCCESS;
+	git_fbuffer fbuf = GIT_FBUFFER_INIT;
+
+	*out = NULL;
+
+	if ((error = git_futils_readbuffer(&fbuf, path)) < GIT_SUCCESS ||
+		(error = git_attr_file__from_buffer(out, fbuf.data)) < GIT_SUCCESS)
+	{
+		git__rethrow(error, "Could not open attribute file '%s'", path);
+	} else {
+		/* save path (okay to fail) */
+		(*out)->path = git__strdup(path);
+	}
+
+	git_futils_freebuffer(&fbuf);
+
+	return error;
+}
+
+void git_attr_file__free(git_attr_file *file)
+{
+	unsigned int i;
+	git_attr_rule *rule;
+
+	if (!file)
+		return;
+
+	git_vector_foreach(&file->rules, i, rule) {
+		free_rule(rule);
+	}
+
+	git_vector_free(&file->rules);
+
+	git__free(file->path);
+	file->path = NULL;
+}
+
+unsigned long git_attr_file__name_hash(const char *name)
+{
+	unsigned long h = 5381;
+	int c;
+	assert(name);
+	while ((c = (int)*name++) != 0)
+		h = ((h << 5) + h) + c;
+	return h;
+}
+
+
+int git_attr_file__lookup_one(
+	git_attr_file *file,
+	const git_attr_path *path,
+	const char *attr,
+	const char **value)
+{
+	unsigned int i;
+	git_attr_name name;
+	git_attr_rule *rule;
+
+	*value = NULL;
+
+	name.name = attr;
+	name.name_hash = git_attr_file__name_hash(attr);
+
+	git_attr_file__foreach_matching_rule(file, path, i, rule) {
+		int pos = git_vector_bsearch(&rule->assigns, &name);
+		git_clearerror(); /* okay if search failed */
+
+		if (pos >= 0) {
+			*value = ((git_attr_assignment *)
+					  git_vector_get(&rule->assigns, pos))->value;
+			break;
+		}
+	}
+
+	return GIT_SUCCESS;
+}
+
+
+int git_attr_rule__match_path(
+	git_attr_rule *rule,
+	const git_attr_path *path)
+{
+	int matched = FNM_NOMATCH;
+
+	if (rule->match.directory && !path->is_dir)
+		return matched;
+
+	if (rule->match.fullpath)
+		matched = p_fnmatch(rule->match.pattern, path->path, FNM_PATHNAME);
+	else
+		matched = p_fnmatch(rule->match.pattern, path->basename, 0);
+
+	if (rule->match.negative)
+		matched = (matched == GIT_SUCCESS) ? FNM_NOMATCH : GIT_SUCCESS;
+
+	return matched;
+}
+
+git_attr_assignment *git_attr_rule__lookup_assignment(
+	git_attr_rule *rule, const char *name)
+{
+	int pos;
+	git_attr_name key;
+	key.name = name;
+	key.name_hash = git_attr_file__name_hash(name);
+
+	pos = git_vector_bsearch(&rule->assigns, &key);
+	git_clearerror(); /* okay if search failed */
+
+	return (pos >= 0) ? git_vector_get(&rule->assigns, pos) : NULL;
+}
+
+int git_attr_path__init(
+	git_attr_path *info, const char *path)
+{
+	info->path = path;
+	info->basename = strrchr(path, '/');
+	if (info->basename)
+		info->basename++;
+	if (!info->basename || !*info->basename)
+		info->basename = path;
+	info->is_dir = (git_futils_isdir(path) == GIT_SUCCESS);
+	return GIT_SUCCESS;
+}
+
+
+/*
+ * From gitattributes(5):
+ *
+ * Patterns have the following format:
+ *
+ * - A blank line matches no files, so it can serve as a separator for
+ *   readability.
+ *
+ * - A line starting with # serves as a comment.
+ *
+ * - An optional prefix ! which negates the pattern; any matching file
+ *   excluded by a previous pattern will become included again. If a negated
+ *   pattern matches, this will override lower precedence patterns sources.
+ *
+ * - If the pattern ends with a slash, it is removed for the purpose of the
+ *   following description, but it would only find a match with a directory. In
+ *   other words, foo/ will match a directory foo and paths underneath it, but
+ *   will not match a regular file or a symbolic link foo (this is consistent
+ *   with the way how pathspec works in general in git).
+ *
+ * - If the pattern does not contain a slash /, git treats it as a shell glob
+ *   pattern and checks for a match against the pathname without leading
+ *   directories.
+ *
+ * - Otherwise, git treats the pattern as a shell glob suitable for consumption
+ *   by fnmatch(3) with the FNM_PATHNAME flag: wildcards in the pattern will
+ *   not match a / in the pathname. For example, "Documentation/\*.html" matches
+ *   "Documentation/git.html" but not "Documentation/ppc/ppc.html". A leading
+ *   slash matches the beginning of the pathname; for example, "/\*.c" matches
+ *   "cat-file.c" but not "mozilla-sha1/sha1.c".
+ */
+
+/*
+ * This will return GIT_SUCCESS if the spec was filled out,
+ * GIT_ENOTFOUND if the fnmatch does not require matching, or
+ * another error code there was an actual problem.
+ */
+static int parse_fnmatch(
+	git_attr_fnmatch *spec,
+	const char **base)
+{
+	const char *pattern;
+	const char *scan;
+	int slash_count;
+	int error = GIT_SUCCESS;
+
+	assert(base && *base);
+
+	pattern = *base;
+
+	while (isspace(*pattern)) pattern++;
+	if (!*pattern || *pattern == '#') {
+		error = GIT_ENOTFOUND;
+		goto skip_to_eol;
+	}
+
+	if (*pattern == '!') {
+		spec->negative = 1;
+		pattern++;
+	} else {
+		spec->negative = 0;
+	}
+
+	spec->fullpath = 0;
+	slash_count = 0;
+	for (scan = pattern; *scan != '\0'; ++scan) {
+		if (isspace(*scan) && *(scan - 1) != '\\')
+			break;
+
+		if (*scan == '/') {
+			spec->fullpath = 1;
+			slash_count++;
+		}
+	}
+
+	*base = scan;
+	spec->length = scan - pattern;
+	spec->pattern = git__strndup(pattern, spec->length);
+
+	if (!spec->pattern) {
+		error = GIT_ENOMEM;
+		goto skip_to_eol;
+	} else {
+		char *from = spec->pattern, *to = spec->pattern;
+		while (*from) {
+			if (*from == '\\') {
+				from++;
+				spec->length--;
+			}
+			*to++ = *from++;
+		}
+		*to = '\0';
+	}
+
+	if (pattern[spec->length - 1] == '/') {
+		spec->length--;
+		spec->pattern[spec->length] = '\0';
+		spec->directory = 1;
+		if (--slash_count <= 0)
+			spec->fullpath = 0;
+	} else {
+		spec->directory = 0;
+	}
+
+	return GIT_SUCCESS;
+
+skip_to_eol:
+	/* skip to end of line */
+	while (*pattern && *pattern != '\n') pattern++;
+	if (*pattern == '\n') pattern++;
+	*base = pattern;
+
+	return error;
+}
+
+static int sort_by_hash_and_name(const void *a_raw, const void *b_raw)
+{
+	const git_attr_name *a = a_raw;
+	const git_attr_name *b = b_raw;
+
+	if (b->name_hash < a->name_hash)
+		return 1;
+	else if (b->name_hash > a->name_hash)
+		return -1;
+	else
+		return strcmp(b->name, a->name);
+}
+
+static int parse_assigns(
+	git_vector *assigns,
+	const char **base)
+{
+	int error = GIT_SUCCESS;
+	const char *scan = *base;
+	git_attr_assignment *assign = NULL;
+
+	assert(assigns && !assigns->length);
+
+	while (*scan && *scan != '\n') {
+		const char *name_start, *value_start;
+
+		/* skip leading blanks */
+		while (isspace(*scan) && *scan != '\n') scan++;
+
+		/* allocate assign if needed */
+		if (!assign) {
+			assign = git__calloc(1, sizeof(git_attr_assignment));
+			if (!assign) {
+				error = GIT_ENOMEM;
+				break;
+			}
+		}
+
+		assign->name_hash = 5381;
+		assign->value = GIT_ATTR_TRUE;
+		assign->is_allocated = 0;
+
+		/* look for magic name prefixes */
+		if (*scan == '-') {
+			assign->value = GIT_ATTR_FALSE;
+			scan++;
+		} else if (*scan == '!') {
+			assign->value = NULL; /* explicit unspecified state */
+			scan++;
+		} else if (*scan == '#') /* comment rest of line */
+			break;
+
+		/* find the name */
+		name_start = scan;
+		while (*scan && !isspace(*scan) && *scan != '=') {
+			assign->name_hash =
+				((assign->name_hash << 5) + assign->name_hash) + *scan;
+			scan++;
+		}
+		assign->name_len = scan - name_start;
+		if (assign->name_len <= 0) {
+			/* must have found lone prefix (" - ") or leading = ("=foo")
+			 * or end of buffer -- advance until whitespace and continue
+			 */
+			while (*scan && !isspace(*scan)) scan++;
+			continue;
+		}
+
+		/* if there is an equals sign, find the value */
+		if (*scan == '=') {
+			for (value_start = ++scan; *scan && !isspace(*scan); ++scan);
+
+			/* if we found a value, allocate permanent storage for it */
+			if (scan > value_start) {
+				assign->value = git__strndup(value_start, scan - value_start);
+				if (!assign->value) {
+					error = GIT_ENOMEM;
+					break;
+				} else {
+					assign->is_allocated = 1;
+				}
+			}
+		}
+
+		/* allocate permanent storage for name */
+		assign->name = git__strndup(name_start, assign->name_len);
+		if (!assign->name) {
+			error = GIT_ENOMEM;
+			break;
+		}
+
+		/* insert allocated assign into vector */
+		error = git_vector_insert(assigns, assign);
+		if (error < GIT_SUCCESS)
+			break;
+
+		/* clear assign since it is now "owned" by the vector */
+		assign = NULL;
+	}
+
+	if (!assigns->length)
+		error = git__throw(GIT_ENOTFOUND, "No attribute assignments found for rule");
+	else {
+		assigns->_cmp = sort_by_hash_and_name;
+		git_vector_sort(assigns);
+	}
+
+	if (assign != NULL) {
+		git__free(assign->name);
+		if (assign->is_allocated)
+			git__free((void *)assign->value);
+		git__free(assign);
+	}
+
+	while (*scan && *scan != '\n') scan++;
+	*base = scan;
+
+	return error;
+}
+
+static int free_rule(git_attr_rule *rule)
+{
+	unsigned int i;
+	git_attr_assignment *assign;
+
+	if (!rule)
+		return GIT_SUCCESS;
+
+	git__free(rule->match.pattern);
+	rule->match.pattern = NULL;
+	rule->match.length = 0;
+
+	git_vector_foreach(&rule->assigns, i, assign) {
+		git__free(assign->name);
+		assign->name = NULL;
+
+		if (assign->is_allocated) {
+			git__free((void *)assign->value);
+			assign->value = NULL;
+		}
+	}
+
+	return GIT_SUCCESS;
+}