[PATCH v2 04/10] evolve: add support for parsing metacommits

["Stefan Xenos via GitGitGadget" <gitgitgadget@gmail.com>]

From: Stefan Xenos <sxenos@google.com>

This patch adds the get_metacommit_content method, which can classify
commits as either metacommits or normal commits, determine whether they
are abandoned, and extract the content commit's object id from the
metacommit.

Signed-off-by: Stefan Xenos <sxenos@google.com>
Signed-off-by: Chris Poucet <poucet@google.com>
---
 Makefile            |  1 +
 commit.c            | 13 ++++++
 commit.h            |  5 +++
 metacommit-parser.c | 97 +++++++++++++++++++++++++++++++++++++++++++++
 metacommit-parser.h | 19 +++++++++
 5 files changed, 135 insertions(+)
 create mode 100644 metacommit-parser.c
 create mode 100644 metacommit-parser.h

diff --git a/Makefile b/Makefile
index cac3452edb9..b2bcc00c289 100644
--- a/Makefile
+++ b/Makefile
@@ -999,6 +999,7 @@ LIB_OBJS += merge-ort.o
 LIB_OBJS += merge-ort-wrappers.o
 LIB_OBJS += merge-recursive.o
 LIB_OBJS += merge.o
+LIB_OBJS += metacommit-parser.o
 LIB_OBJS += midx.o
 LIB_OBJS += name-hash.o
 LIB_OBJS += negotiator/default.o
diff --git a/commit.c b/commit.c
index 89b8efc6116..3eabb66fb6b 100644
--- a/commit.c
+++ b/commit.c
@@ -623,6 +623,19 @@ struct commit_list *reverse_commit_list(struct commit_list *list)
 	return next;
 }
 
+struct commit *get_commit_by_index(struct commit_list *to_search, int index)
+{
+	while (to_search && index) {
+		to_search = to_search->next;
+		index--;
+	}
+
+	if (!to_search)
+		return NULL;
+
+	return to_search->item;
+}
+
 void free_commit_list(struct commit_list *list)
 {
 	while (list)
diff --git a/commit.h b/commit.h
index 21e4d25ce78..11861a5a78c 100644
--- a/commit.h
+++ b/commit.h
@@ -188,8 +188,13 @@ struct commit_list *copy_commit_list(struct commit_list *list);
 /* Modify list in-place to reverse it, returning new head; list will be tail */
 struct commit_list *reverse_commit_list(struct commit_list *list);
 
+/* Returns the commit at `index` or NULL if the index exceeds the `to_search`
+ * list */
+struct commit *get_commit_by_index(struct commit_list *to_search, int index);
+
 void free_commit_list(struct commit_list *list);
 
+
 struct rev_info; /* in revision.h, it circularly uses enum cmit_fmt */
 
 int has_non_ascii(const char *text);
diff --git a/metacommit-parser.c b/metacommit-parser.c
new file mode 100644
index 00000000000..baccfb4dd5c
--- /dev/null
+++ b/metacommit-parser.c
@@ -0,0 +1,97 @@
+#include "cache.h"
+#include "metacommit-parser.h"
+#include "commit.h"
+
+/*
+ * Search the commit buffer for a line starting with the given key. Unlike
+ * find_commit_header, this also searches the commit message body.
+ */
+static const char *find_key(const char *msg, const char *key, size_t *out_len)
+{
+	int key_len = strlen(key);
+	const char *line = msg;
+
+	while (line) {
+		const char *eol = strchrnul(line, '\n');
+
+		if (eol - line > key_len && !memcmp(line, key, key_len) &&
+		    line[key_len] == ' ') {
+			*out_len = eol - line - key_len - 1;
+			return line + key_len + 1;
+		}
+		line = *eol ? eol + 1 : NULL;
+	}
+	return NULL;
+}
+
+/*
+ * Writes the index of the content parent to "result". Returns the metacommit
+ * type. See the METACOMMIT_TYPE_* constants.
+ */
+static enum metacommit_type index_of_content_commit(const char *buffer, int *result)
+{
+	int index = 0;
+	int ret = METACOMMIT_TYPE_NONE;
+	size_t parent_types_size;
+	const char *parent_types = find_key(buffer, "parent-type",
+		&parent_types_size);
+	const char *end;
+	const char *enum_start = parent_types;
+	int enum_length = 0;
+
+	if (!parent_types)
+		return METACOMMIT_TYPE_NONE;
+
+	end = &parent_types[parent_types_size];
+
+	while (1) {
+		char next = *parent_types;
+		if (next == ' ' || parent_types >= end) {
+			if (enum_length == 1) {
+				char type = *enum_start;
+				if (type == 'c') {
+					ret = METACOMMIT_TYPE_NORMAL;
+					break;
+				}
+				if (type == 'a') {
+					ret = METACOMMIT_TYPE_ABANDONED;
+					break;
+				}
+			}
+			if (parent_types >= end)
+				return METACOMMIT_TYPE_NONE;
+			enum_start = parent_types + 1;
+			enum_length = 0;
+			index++;
+		} else {
+			enum_length++;
+		}
+		parent_types++;
+	}
+
+	*result = index;
+	return ret;
+}
+
+/*
+ * Writes the content parent's object id to "content".
+ * Returns the metacommit type. See the METACOMMIT_TYPE_* constants.
+ */
+enum metacommit_type get_metacommit_content(struct commit *commit, struct object_id *content)
+{
+	const char *buffer = get_commit_buffer(commit, NULL);
+	int index = 0;
+	enum metacommit_type ret = index_of_content_commit(buffer, &index);
+	struct commit *content_parent;
+
+	if (ret == METACOMMIT_TYPE_NONE)
+		return ret;
+
+	content_parent = get_commit_by_index(commit->parents, index);
+
+	if (!content_parent)
+		return METACOMMIT_TYPE_NONE;
+
+	oidcpy(content, &(content_parent->object.oid));
+	return ret;
+}
diff --git a/metacommit-parser.h b/metacommit-parser.h
new file mode 100644
index 00000000000..ef4a121d433
--- /dev/null
+++ b/metacommit-parser.h
@@ -0,0 +1,19 @@
+#ifndef METACOMMIT_PARSER_H
+#define METACOMMIT_PARSER_H
+
+#include "commit.h"
+#include "hash.h"
+
+enum metacommit_type {
+	/* Indicates a normal commit (non-metacommit) */
+	METACOMMIT_TYPE_NONE = 0,
+	/* Indicates a metacommit with normal content (non-abandoned) */
+	METACOMMIT_TYPE_NORMAL = 1,
+	/* Indicates a metacommit with abandoned content */
+	METACOMMIT_TYPE_ABANDONED = 2,
+};
+
+enum metacommit_type get_metacommit_content(
+	struct commit *commit, struct object_id *content);
+
+#endif
-- 
gitgitgadget