Merge pull request #4451 from libgit2/charliesome/trailer-info

Implement message trailer parsing API

3 files changed, 622 insertions, 0 deletions

diff --git a/include/git2/message.h b/include/git2/message.h
index d78b1dce5..329346285 100644
--- a/include/git2/message.h
+++ b/include/git2/message.h
@@ -38,6 +38,47 @@ GIT_BEGIN_DECL
  */
 GIT_EXTERN(int) git_message_prettify(git_buf *out, const char *message, int strip_comments, char comment_char);
 
+/**
+ * Represents a single git message trailer.
+ */
+typedef struct {
+  const char *key;
+  const char *value;
+} git_message_trailer;
+
+/**
+ * Represents an array of git message trailers.
+ *
+ * Struct members under the private comment are private, subject to change
+ * and should not be used by callers.
+ */
+typedef struct {
+  git_message_trailer *trailers;
+  size_t count;
+
+  /* private */
+  char *_trailer_block;
+} git_message_trailer_array;
+
+/**
+ * Parse trailers out of a message, filling the array pointed to by +arr+.
+ *
+ * Trailers are key/value pairs in the last paragraph of a message, not
+ * including any patches or conflicts that may be present.
+ *
+ * @param arr A pre-allocated git_message_trailer_array struct to be filled in
+ *            with any trailers found during parsing.
+ * @param message The message to be parsed
+ * @return 0 on success, or non-zero on error.
+ */
+GIT_EXTERN(int) git_message_trailers(git_message_trailer_array *arr, const char *message);
+
+/**
+ * Clean's up any allocated memory in the git_message_trailer_array filled by
+ * a call to git_message_trailers.
+ */
+GIT_EXTERN(void) git_message_trailer_array_free(git_message_trailer_array *arr);
+
 /** @} */
 GIT_END_DECL
 
diff --git a/src/trailer.c b/src/trailer.c
new file mode 100644
index 000000000..24c8847f6
--- /dev/null
+++ b/src/trailer.c
@@ -0,0 +1,416 @@
+/*
+ * Copyright (C) the libgit2 contributors. All rights reserved.
+ *
+ * This file is part of libgit2, distributed under the GNU GPL v2 with
+ * a Linking Exception. For full terms see the included COPYING file.
+ */
+#include "array.h"
+#include "common.h"
+#include "git2/message.h"
+
+#include <stddef.h>
+#include <string.h>
+#include <ctype.h>
+
+#define COMMENT_LINE_CHAR '#'
+#define TRAILER_SEPARATORS ":"
+
+static const char *const git_generated_prefixes[] = {
+	"Signed-off-by: ",
+	"(cherry picked from commit ",
+	NULL
+};
+
+static int is_blank_line(const char *str)
+{
+	const char *s = str;
+	while (*s && *s != '\n' && isspace(*s))
+		s++;
+	return !*s || *s == '\n';
+}
+
+static const char *next_line(const char *str)
+{
+	const char *nl = strchr(str, '\n');
+
+	if (nl) {
+		return nl + 1;
+	} else {
+		// return pointer to the NUL terminator:
+		return str + strlen(str);
+	}
+}
+
+/*
+ * Return the position of the start of the last line. If len is 0, return -1.
+ */
+static int last_line(const char *buf, size_t len)
+{
+	int i;
+	if (len == 0)
+		return -1;
+	if (len == 1)
+		return 0;
+	/*
+	 * Skip the last character (in addition to the null terminator),
+	 * because if the last character is a newline, it is considered as part
+	 * of the last line anyway.
+	 */
+	i = len - 2;
+
+	for (; i >= 0; i--) {
+		if (buf[i] == '\n')
+			return i + 1;
+	}
+	return 0;
+}
+
+/*
+ * If the given line is of the form
+ * "<token><optional whitespace><separator>..." or "<separator>...", return the
+ * location of the separator. Otherwise, return -1.  The optional whitespace
+ * is allowed there primarily to allow things like "Bug #43" where <token> is
+ * "Bug" and <separator> is "#".
+ *
+ * The separator-starts-line case (in which this function returns 0) is
+ * distinguished from the non-well-formed-line case (in which this function
+ * returns -1) because some callers of this function need such a distinction.
+ */
+static int find_separator(const char *line, const char *separators)
+{
+	int whitespace_found = 0;
+	const char *c;
+	for (c = line; *c; c++) {
+		if (strchr(separators, *c))
+			return c - line;
+		if (!whitespace_found && (isalnum(*c) || *c == '-'))
+			continue;
+		if (c != line && (*c == ' ' || *c == '\t')) {
+			whitespace_found = 1;
+			continue;
+		}
+		break;
+	}
+	return -1;
+}
+
+/*
+ * Inspect the given string and determine the true "end" of the log message, in
+ * order to find where to put a new Signed-off-by: line.  Ignored are
+ * trailing comment lines and blank lines.  To support "git commit -s
+ * --amend" on an existing commit, we also ignore "Conflicts:".  To
+ * support "git commit -v", we truncate at cut lines.
+ *
+ * Returns the number of bytes from the tail to ignore, to be fed as
+ * the second parameter to append_signoff().
+ */
+static int ignore_non_trailer(const char *buf, size_t len)
+{
+	int boc = 0;
+	size_t bol = 0;
+	int in_old_conflicts_block = 0;
+	size_t cutoff = len;
+
+	while (bol < cutoff) {
+		const char *next_line = memchr(buf + bol, '\n', len - bol);
+
+		if (!next_line)
+			next_line = buf + len;
+		else
+			next_line++;
+
+		if (buf[bol] == COMMENT_LINE_CHAR || buf[bol] == '\n') {
+			/* is this the first of the run of comments? */
+			if (!boc)
+				boc = bol;
+			/* otherwise, it is just continuing */
+		} else if (git__prefixcmp(buf + bol, "Conflicts:\n") == 0) {
+			in_old_conflicts_block = 1;
+			if (!boc)
+				boc = bol;
+		} else if (in_old_conflicts_block && buf[bol] == '\t') {
+			; /* a pathname in the conflicts block */
+		} else if (boc) {
+			/* the previous was not trailing comment */
+			boc = 0;
+			in_old_conflicts_block = 0;
+		}
+		bol = next_line - buf;
+	}
+	return boc ? len - boc : len - cutoff;
+}
+
+/*
+ * Return the position of the start of the patch or the length of str if there
+ * is no patch in the message.
+ */
+static int find_patch_start(const char *str)
+{
+	const char *s;
+
+	for (s = str; *s; s = next_line(s)) {
+		if (git__prefixcmp(s, "---") == 0)
+			return s - str;
+	}
+
+	return s - str;
+}
+
+/*
+ * Return the position of the first trailer line or len if there are no
+ * trailers.
+ */
+static int find_trailer_start(const char *buf, size_t len)
+{
+	const char *s;
+	int end_of_title, l, only_spaces = 1;
+	int recognized_prefix = 0, trailer_lines = 0, non_trailer_lines = 0;
+	/*
+	 * Number of possible continuation lines encountered. This will be
+	 * reset to 0 if we encounter a trailer (since those lines are to be
+	 * considered continuations of that trailer), and added to
+	 * non_trailer_lines if we encounter a non-trailer (since those lines
+	 * are to be considered non-trailers).
+	 */
+	int possible_continuation_lines = 0;
+
+	/* The first paragraph is the title and cannot be trailers */
+	for (s = buf; s < buf + len; s = next_line(s)) {
+		if (s[0] == COMMENT_LINE_CHAR)
+			continue;
+		if (is_blank_line(s))
+			break;
+	}
+	end_of_title = s - buf;
+
+	/*
+	 * Get the start of the trailers by looking starting from the end for a
+	 * blank line before a set of non-blank lines that (i) are all
+	 * trailers, or (ii) contains at least one Git-generated trailer and
+	 * consists of at least 25% trailers.
+	 */
+	for (l = last_line(buf, len);
+	     l >= end_of_title;
+	     l = last_line(buf, l)) {
+		const char *bol = buf + l;
+		const char *const *p;
+		int separator_pos;
+
+		if (bol[0] == COMMENT_LINE_CHAR) {
+			non_trailer_lines += possible_continuation_lines;
+			possible_continuation_lines = 0;
+			continue;
+		}
+		if (is_blank_line(bol)) {
+			if (only_spaces)
+				continue;
+			non_trailer_lines += possible_continuation_lines;
+			if (recognized_prefix &&
+			    trailer_lines * 3 >= non_trailer_lines)
+				return next_line(bol) - buf;
+			else if (trailer_lines && !non_trailer_lines)
+				return next_line(bol) - buf;
+			return len;
+		}
+		only_spaces = 0;
+
+		for (p = git_generated_prefixes; *p; p++) {
+			if (git__prefixcmp(bol, *p) == 0) {
+				trailer_lines++;
+				possible_continuation_lines = 0;
+				recognized_prefix = 1;
+				goto continue_outer_loop;
+			}
+		}
+
+		separator_pos = find_separator(bol, TRAILER_SEPARATORS);
+		if (separator_pos >= 1 && !isspace(bol[0])) {
+			trailer_lines++;
+			possible_continuation_lines = 0;
+			if (recognized_prefix)
+				continue;
+		} else if (isspace(bol[0]))
+			possible_continuation_lines++;
+		else {
+			non_trailer_lines++;
+			non_trailer_lines += possible_continuation_lines;
+			possible_continuation_lines = 0;
+		}
+continue_outer_loop:
+		;
+	}
+
+	return len;
+}
+
+/* Return the position of the end of the trailers. */
+static int find_trailer_end(const char *buf, size_t len)
+{
+	return len - ignore_non_trailer(buf, len);
+}
+
+static char *extract_trailer_block(const char *message, size_t* len)
+{
+	size_t patch_start = find_patch_start(message);
+	size_t trailer_end = find_trailer_end(message, patch_start);
+	size_t trailer_start = find_trailer_start(message, trailer_end);
+
+	size_t trailer_len = trailer_end - trailer_start;
+
+	char *buffer = git__malloc(trailer_len + 1);
+	memcpy(buffer, message + trailer_start, trailer_len);
+	buffer[trailer_len] = 0;
+
+	*len = trailer_len;
+
+	return buffer;
+}
+
+enum trailer_state {
+	S_START = 0,
+	S_KEY = 1,
+	S_KEY_WS = 2,
+	S_SEP_WS = 3,
+	S_VALUE = 4,
+	S_VALUE_NL = 5,
+	S_VALUE_END = 6,
+	S_IGNORE = 7,
+};
+
+#define NEXT(st) { state = (st); ptr++; continue; }
+#define GOTO(st) { state = (st); continue; }
+
+typedef git_array_t(git_message_trailer) git_array_trailer_t;
+
+int git_message_trailers(git_message_trailer_array *trailer_arr, const char *message)
+{
+	enum trailer_state state = S_START;
+	int rc = 0;
+	char *ptr;
+	char *key = NULL;
+	char *value = NULL;
+	git_array_trailer_t arr = GIT_ARRAY_INIT;
+
+	size_t trailer_len;
+	char *trailer = extract_trailer_block(message, &trailer_len);
+
+	for (ptr = trailer;;) {
+		switch (state) {
+			case S_START: {
+				if (*ptr == 0) {
+					goto ret;
+				}
+
+				key = ptr;
+				GOTO(S_KEY);
+			}
+			case S_KEY: {
+				if (*ptr == 0) {
+					goto ret;
+				}
+
+				if (isalnum(*ptr) || *ptr == '-') {
+					// legal key character
+					NEXT(S_KEY);
+				}
+
+				if (*ptr == ' ' || *ptr == '\t') {
+					// optional whitespace before separator
+					*ptr = 0;
+					NEXT(S_KEY_WS);
+				}
+
+				if (strchr(TRAILER_SEPARATORS, *ptr)) {
+					*ptr = 0;
+					NEXT(S_SEP_WS);
+				}
+
+				// illegal character
+				GOTO(S_IGNORE);
+			}
+			case S_KEY_WS: {
+				if (*ptr == 0) {
+					goto ret;
+				}
+
+				if (*ptr == ' ' || *ptr == '\t') {
+					NEXT(S_KEY_WS);
+				}
+
+				if (strchr(TRAILER_SEPARATORS, *ptr)) {
+					NEXT(S_SEP_WS);
+				}
+
+				// illegal character
+				GOTO(S_IGNORE);
+			}
+			case S_SEP_WS: {
+				if (*ptr == 0) {
+					goto ret;
+				}
+
+				if (*ptr == ' ' || *ptr == '\t') {
+					NEXT(S_SEP_WS);
+				}
+
+				value = ptr;
+				NEXT(S_VALUE);
+			}
+			case S_VALUE: {
+				if (*ptr == 0) {
+					GOTO(S_VALUE_END);
+				}
+
+				if (*ptr == '\n') {
+					NEXT(S_VALUE_NL);
+				}
+
+				NEXT(S_VALUE);
+			}
+			case S_VALUE_NL: {
+				if (*ptr == ' ') {
+					// continuation;
+					NEXT(S_VALUE);
+				}
+
+				ptr[-1] = 0;
+				GOTO(S_VALUE_END);
+			}
+			case S_VALUE_END: {
+				git_message_trailer *t = git_array_alloc(arr);
+
+				t->key = key;
+				t->value = value;
+
+				key = NULL;
+				value = NULL;
+
+				GOTO(S_START);
+			}
+			case S_IGNORE: {
+				if (*ptr == 0) {
+					goto ret;
+				}
+
+				if (*ptr == '\n') {
+					NEXT(S_START);
+				}
+
+				NEXT(S_IGNORE);
+			}
+		}
+	}
+
+ret:
+	trailer_arr->_trailer_block = trailer;
+	trailer_arr->trailers = arr.ptr;
+	trailer_arr->count = arr.size;
+
+	return rc;
+}
+
+void git_message_trailer_array_free(git_message_trailer_array *arr)
+{
+	git__free(arr->_trailer_block);
+	git__free(arr->trailers);
+}
diff --git a/tests/message/trailer.c b/tests/message/trailer.c
new file mode 100644
index 000000000..9cc83de72
--- /dev/null
+++ b/tests/message/trailer.c
@@ -0,0 +1,165 @@
+#include "clar_libgit2.h"
+#include "message.h"
+
+static void assert_trailers(const char *message, git_message_trailer *trailers)
+{
+	git_message_trailer_array arr;
+	size_t i;
+
+	int rc = git_message_trailers(&arr, message);
+
+	cl_assert_equal_i(0, rc);
+
+	for(i=0; i<arr.count; i++) {
+		cl_assert_equal_s(arr.trailers[i].key, trailers[i].key);
+		cl_assert_equal_s(arr.trailers[i].value, trailers[i].value);
+	}
+
+	cl_assert_equal_i(0, rc);
+
+	git_message_trailer_array_free(&arr);
+}
+
+void test_message_trailer__simple(void)
+{
+	git_message_trailer trailers[] = {
+		{"Signed-off-by", "foo@bar.com"},
+		{"Signed-off-by", "someone@else.com"},
+		{NULL, NULL},
+	};
+
+	assert_trailers(
+		"Message\n"
+		"\n"
+		"Signed-off-by: foo@bar.com\n"
+		"Signed-off-by: someone@else.com\n"
+	, trailers);
+}
+
+void test_message_trailer__no_whitespace(void)
+{
+	git_message_trailer trailers[] = {
+		{"Key", "value"},
+		{NULL, NULL},
+	};
+
+	assert_trailers(
+		"Message\n"
+		"\n"
+		"Key:value\n"
+	, trailers);
+}
+
+void test_message_trailer__extra_whitespace(void)
+{
+	git_message_trailer trailers[] = {
+		{"Key", "value"},
+		{NULL, NULL},
+	};
+
+	assert_trailers(
+		"Message\n"
+		"\n"
+		"Key   :   value\n"
+	, trailers);
+}
+
+void test_message_trailer__no_newline(void)
+{
+	git_message_trailer trailers[] = {
+		{"Key", "value"},
+		{NULL, NULL},
+	};
+
+	assert_trailers(
+		"Message\n"
+		"\n"
+		"Key: value"
+	, trailers);
+}
+
+void test_message_trailer__not_last_paragraph(void)
+{
+	git_message_trailer trailers[] = {
+		{NULL, NULL},
+	};
+
+	assert_trailers(
+		"Message\n"
+		"\n"
+		"Key: value\n"
+		"\n"
+		"More stuff\n"
+	, trailers);
+}
+
+void test_message_trailer__conflicts(void)
+{
+	git_message_trailer trailers[] = {
+		{"Key", "value"},
+		{NULL, NULL},
+	};
+
+	assert_trailers(
+		"Message\n"
+		"\n"
+		"Key: value\n"
+		"\n"
+		"Conflicts:\n"
+		"\tfoo.c\n"
+	, trailers);
+}
+
+void test_message_trailer__patch(void)
+{
+	git_message_trailer trailers[] = {
+		{"Key", "value"},
+		{NULL, NULL},
+	};
+
+	assert_trailers(
+		"Message\n"
+		"\n"
+		"Key: value\n"
+		"\n"
+		"---\n"
+		"More: stuff\n"
+	, trailers);
+}
+
+void test_message_trailer__continuation(void)
+{
+	git_message_trailer trailers[] = {
+		{"A", "b\n c"},
+		{"D", "e\n f: g h"},
+		{"I", "j"},
+		{NULL, NULL},
+	};
+
+	assert_trailers(
+		"Message\n"
+		"\n"
+		"A: b\n"
+		" c\n"
+		"D: e\n"
+		" f: g h\n"
+		"I: j\n"
+	, trailers);
+}
+
+void test_message_trailer__invalid(void)
+{
+	git_message_trailer trailers[] = {
+		{"Signed-off-by", "some@one.com"},
+		{"Another", "trailer"},
+		{NULL, NULL},
+	};
+
+	assert_trailers(
+		"Message\n"
+		"\n"
+		"Signed-off-by: some@one.com\n"
+		"Not a trailer\n"
+		"Another: trailer\n"
+	, trailers);
+}