Merge branch 'diff-crlf-filters' into development

include/git2/diff.h

@@ -56,7 +56,13 @@ enum {
  * values.  Similarly, passing NULL for the options structure will
  * give the defaults.  The default values are marked below.
  *
- * @todo Most of the parameters here are not actually supported at this time.
+ * - flags: a combination of the GIT_DIFF_... values above
+ * - context_lines: number of lines of context to show around diffs
+ * - interhunk_lines: min lines between diff hunks to merge them
+ * - old_prefix: "directory" to prefix to old file names (default "a")
+ * - new_prefix: "directory" to prefix to new file names (default "b")
+ * - pathspec: array of paths / patterns to constrain diff
+ * - max_size: maximum blob size to diff, above this treated as binary
  */
 typedef struct {
 	uint32_t flags;				/**< defaults to GIT_DIFF_NORMAL */
@@ -65,6 +71,7 @@ typedef struct {
 	char *old_prefix;			/**< defaults to "a" */
 	char *new_prefix;			/**< defaults to "b" */
 	git_strarray pathspec;		/**< defaults to show all paths */
+	git_off_t max_size;			/**< defaults to 512Mb */
 } git_diff_options;
 
 /**
@@ -72,13 +79,28 @@ typedef struct {
  */
 typedef struct git_diff_list git_diff_list;
 
+/**
+ * Flags that can be set for the file on side of a diff.
+ *
+ * Most of the flags are just for internal consumption by libgit2,
+ * but some of them may be interesting to external users.  They are:
+ *
+ * - VALID_OID  - the `oid` value is computed and correct
+ * - FREE_PATH  - the `path` string is separated allocated memory
+ * - BINARY     - this file should be considered binary data
+ * - NOT_BINARY - this file should be considered text data
+ * - FREE_DATA  - the internal file data is kept in allocated memory
+ * - UNMAP_DATA - the internal file data is kept in mmap'ed memory
+ * - NO_DATA    - this side of the diff should not be loaded
+ */
 enum {
 	GIT_DIFF_FILE_VALID_OID  = (1 << 0),
 	GIT_DIFF_FILE_FREE_PATH  = (1 << 1),
 	GIT_DIFF_FILE_BINARY     = (1 << 2),
 	GIT_DIFF_FILE_NOT_BINARY = (1 << 3),
 	GIT_DIFF_FILE_FREE_DATA  = (1 << 4),
-	GIT_DIFF_FILE_UNMAP_DATA = (1 << 5)
+	GIT_DIFF_FILE_UNMAP_DATA = (1 << 5),
+	GIT_DIFF_FILE_NO_DATA    = (1 << 6),
 };
 
 /**
@@ -169,7 +191,7 @@ enum {
 	GIT_DIFF_LINE_CONTEXT   = ' ',
 	GIT_DIFF_LINE_ADDITION  = '+',
 	GIT_DIFF_LINE_DELETION  = '-',
-	GIT_DIFF_LINE_ADD_EOFNL = '\n', /**< DEPRECATED - will not be returned */
+	GIT_DIFF_LINE_ADD_EOFNL = '\n', /**< Removed line w/o LF & added one with */
 	GIT_DIFF_LINE_DEL_EOFNL = '\0', /**< LF was removed at end of file */
 
 	/* The following values will only be sent to a `git_diff_data_fn` when
@@ -384,25 +406,16 @@ GIT_EXTERN(int) git_diff_iterator_new(
 GIT_EXTERN(void) git_diff_iterator_free(git_diff_iterator *iterator);
 
 /**
- * Return the number of files in the diff.
- *
- * Note that there is an uncommon scenario where this number might be too
- * high -- if a file in the working directory has been "touched" on disk but
- * the contents were then reverted, it might have been added to the
- * `git_diff_list` as a MODIFIED file along with a note that the status
- * needs to be confirmed when the file contents are loaded into memory.  In
- * that case, when the file is loaded, we will check the contents and might
- * switch it back to UNMODIFIED.  The loading of the file is deferred until
- * as late as possible.  As a result, this might return a value what was too
- * high in those circumstances.
+ * Return progress value for traversing the diff.
  *
- * This is true of `git_diff_foreach` as well, but the only implication
- * there is that the `progress` value would not advance evenly.
+ * This returns a value between 0.0 and 1.0 that represents the progress
+ * through the diff iterator.  The value is monotonically increasing and
+ * will advance gradually as you progress through the iteration.
  *
- * @param iterator The iterator object
- * @return The maximum number of files to be iterated over
+ * @param iterator The diff iterator
+ * @return Value between 0.0 and 1.0
  */
-GIT_EXTERN(int) git_diff_iterator_num_files(git_diff_iterator *iterator);
+GIT_EXTERN(float) git_diff_iterator_progress(git_diff_iterator *iterator);
 
 /**
  * Return the number of hunks in the current file
@@ -450,16 +463,19 @@ GIT_EXTERN(int) git_diff_iterator_next_file(
  * It is recommended that you not call this if the file is a binary
  * file, but it is allowed to do so.
  *
- * Warning! Call this function for the first time on a file is when the
+ * The `header` text output will contain the standard hunk header that
+ * would appear in diff output.  The header string will be NUL terminated.
+ *
+ * WARNING! Call this function for the first time on a file is when the
  * actual text diff will be computed (it cannot be computed incrementally)
  * so the first call for a new file is expensive (at least in relative
  * terms - in reality, it is still pretty darn fast).
  *
- * @param range Pointer where to store the range for the hunk 
- * @param header Pointer where to store the header for the chunk;
- *	this string is owned by the library and should not be freed by
- *	the user
- * @param header_len Pointer where to store the length of the returned header
+ * @param range Output pointer to range of lines covered by the hunk;
+ *        This range object is owned by the library and should not be freed.
+ * @param header Output pointer to the text of the hunk header
+ *        This string is owned by the library and should not be freed.
+ * @param header_len Output pointer to store the length of the header text
  * @param iterator The iterator object
  * @return 0 on success, GIT_ITEROVER when done with current file, other
  *         value < 0 on error
@@ -473,12 +489,18 @@ GIT_EXTERN(int) git_diff_iterator_next_hunk(
 /**
  * Return the next line of the current hunk of diffs.
  *
- * @param line_origin Pointer where to store a GIT_DIFF_LINE_ value;
- *	this value is a single character, not a buffer
- * @param content Pointer where to store the content of the line;
- *	this string is owned by the library and should not be freed by
- *	the user
- * @param Pointer where to store the length of the returned content
+ * The `line_origin` output will tell you what type of line this is
+ * (e.g. was it added or removed or is it just context for the diff).
+ *
+ * The `content` will be a pointer to the file data that goes in the
+ * line. IT WILL NOT BE NUL TERMINATED. You have to use the `content_len`
+ * value and only process that many bytes of data from the content string.
+ *
+ * @param line_origin Output pointer to store a GIT_DIFF_LINE value for this
+ *        next chunk of data. The value is a single character, not a buffer.
+ * @param content Output pointer to store the content of the diff; this
+ *        string is owned by the library and should not be freed.
+ * @param content_len Output pointer to store the length of the content.
  * @param iterator The iterator object
  * @return 0 on success, GIT_ITEROVER when done with current line, other
  *         value < 0 on error

src/amiga/map.c

@@ -24,18 +24,15 @@ int p_mmap(git_map *out, size_t len, int prot, int flags, int fd, git_off_t offs
 		return -1;
 	}
 
-	if((out->data = malloc(len))) {
-		p_lseek(fd, offset, SEEK_SET);
-		p_read(fd, out->data, len);
-	}
+	out->data = malloc(len);
+	GITERR_CHECK_ALLOC(out->data);
 
-	if (!out->data || (out->data == MAP_FAILED)) {
-		giterr_set(GITERR_OS, "Failed to mmap. Could not write data");
+	if (p_lseek(fd, offset, SEEK_SET) < 0 || p_read(fd, out->data, len) != len)
+		giterr_set(GITERR_OS, "mmap emulation failed");
 		return -1;
 	}
 
 	out->len = len;
-
 	return 0;
 }
 

src/blob.c

@@ -68,6 +68,7 @@ static int write_file_stream(
 	int fd, error;
 	char buffer[4096];
 	git_odb_stream *stream = NULL;
+	ssize_t read_len, written = 0;
 
 	if ((error = git_odb_open_wstream(
 			&stream, odb, (size_t)file_size, GIT_OBJ_BLOB)) < 0)
@@ -78,20 +79,18 @@ static int write_file_stream(
 		return -1;
 	}
 
-	while (!error && file_size > 0) {
-		ssize_t read_len = p_read(fd, buffer, sizeof(buffer));
-
-		if (read_len < 0) {
-			giterr_set(
-				GITERR_OS, "Failed to create blob. Can't read whole file");
-			error = -1;
-		}
-		else if (!(error = stream->write(stream, buffer, read_len)))
-			file_size -= read_len;
+	while (!error && (read_len = p_read(fd, buffer, sizeof(buffer))) > 0) {
+		error = stream->write(stream, buffer, read_len);
+		written += read_len;
 	}
 
 	p_close(fd);
 
+	if (written != file_size || read_len < 0) {
+		giterr_set(GITERR_OS, "Failed to read file into stream");
+		error = -1;
+	}
+
 	if (!error)
 		error = stream->finalize_write(oid, stream);
 

src/crlf.c

@@ -276,7 +276,7 @@ static int find_and_add_filter(git_vector *filters, git_repository *repo, const
 
 	/*
 	 * Use the core Git logic to see if we should perform CRLF for this file
-	 * based on its attributes & the value of `core.auto_crlf`
+	 * based on its attributes & the value of `core.autocrlf`
 	 */
 	ca.crlf_action = crlf_input_action(&ca);
 

src/diff.c

@@ -11,6 +11,7 @@
 #include "fileops.h"
 #include "config.h"
 #include "attr_file.h"
+#include "filter.h"
 
 static char *diff_prefix_from_pathspec(const git_strarray *pathspec)
 {
@@ -63,8 +64,8 @@ static bool diff_path_matches_pathspec(git_diff_list *diff, const char *path)
 
 	git_vector_foreach(&diff->pathspec, i, match) {
 		int result = strcmp(match->pattern, path) ? FNM_NOMATCH : 0;
-		
-		if (((diff->opts.flags & GIT_DIFF_DISABLE_PATHSPEC_MATCH) == 0) && 
+
+		if (((diff->opts.flags & GIT_DIFF_DISABLE_PATHSPEC_MATCH) == 0) &&
 			result == FNM_NOMATCH)
 			result = p_fnmatch(match->pattern, path, 0);
 
@@ -262,12 +263,14 @@ static int diff_delta__from_two(
 	delta = diff_delta__alloc(diff, status, old_entry->path);
 	GITERR_CHECK_ALLOC(delta);
 
-	delta->old_file.mode = old_mode;
 	git_oid_cpy(&delta->old_file.oid, &old_entry->oid);
+	delta->old_file.size = old_entry->file_size;
+	delta->old_file.mode = old_mode;
 	delta->old_file.flags |= GIT_DIFF_FILE_VALID_OID;
 
-	delta->new_file.mode = new_mode;
 	git_oid_cpy(&delta->new_file.oid, new_oid ? new_oid : &new_entry->oid);
+	delta->new_file.size = new_entry->file_size;
+	delta->new_file.mode = new_mode;
 	if (new_oid || !git_oid_iszero(&new_entry->oid))
 		delta->new_file.flags |= GIT_DIFF_FILE_VALID_OID;
 
@@ -440,14 +443,22 @@ static int oid_for_workdir_item(
 		giterr_set(GITERR_OS, "File size overflow for 32-bit systems");
 		result = -1;
 	} else {
-		int fd = git_futils_open_ro(full_path.ptr);
-		if (fd < 0)
-			result = fd;
-		else {
-			result = git_odb__hashfd(
-				oid, fd, (size_t)item->file_size, GIT_OBJ_BLOB);
-			p_close(fd);
+		git_vector filters = GIT_VECTOR_INIT;
+
+		result = git_filters_load(
+			&filters, repo, item->path, GIT_FILTER_TO_ODB);
+		if (result >= 0) {
+			int fd = git_futils_open_ro(full_path.ptr);
+			if (fd < 0)
+				result = fd;
+			else {
+				result = git_odb__hashfd_filtered(
+					oid, fd, (size_t)item->file_size, GIT_OBJ_BLOB, &filters);
+				p_close(fd);
+			}
 		}
+
+		git_filters_free(&filters);
 	}
 
 	git_buf_free(&full_path);

src/diff.h

@@ -25,6 +25,8 @@ enum {
 	GIT_DIFFCAPS_USE_DEV          = (1 << 4), /* use st_dev? */
 };
 
+#define MAX_DIFF_FILESIZE 0x20000000
+
 struct git_diff_list {
 	git_refcount     rc;
 	git_repository   *repo;
@@ -40,5 +42,27 @@ struct git_diff_list {
 extern void git_diff__cleanup_modes(
 	uint32_t diffcaps, uint32_t *omode, uint32_t *nmode);
 
+/**
+ * Return the maximum possible number of files in the diff.
+ *
+ * NOTE: This number has to be treated as an upper bound on the number of
+ * files that have changed if the diff is with the working directory.
+ *
+ * Why?! For efficiency, we defer loading the file contents as long as
+ * possible, so if a file has been "touched" in the working directory and
+ * then reverted to the original content, it may get stored in the diff list
+ * as MODIFIED along with a flag that the status should be reconfirmed when
+ * it is actually loaded into memory.  When that load happens, it could get
+ * flipped to UNMODIFIED. If unmodified files are being skipped, then the
+ * iterator will skip that file and this number may be too high.
+ *
+ * This behavior is true of `git_diff_foreach` as well, but the only
+ * implication there is that the `progress` value would not advance evenly.
+ *
+ * @param iterator The iterator object
+ * @return The maximum number of files to be iterated over
+ */
+int git_diff_iterator__max_files(git_diff_iterator *iterator);
+
 #endif
 

src/filebuf.c

@@ -73,7 +73,7 @@ static int lock_file(git_filebuf *file, int flags)
 	if ((flags & GIT_FILEBUF_APPEND) && git_path_exists(file->path_original) == true) {
 		git_file source;
 		char buffer[2048];
-		size_t read_bytes;
+		ssize_t read_bytes;
 
 		source = p_open(file->path_original, O_RDONLY);
 		if (source < 0) {
@@ -83,13 +83,18 @@ static int lock_file(git_filebuf *file, int flags)
 			return -1;
 		}
 
-		while ((read_bytes = p_read(source, buffer, 2048)) > 0) {
+		while ((read_bytes = p_read(source, buffer, sizeof(buffer))) > 0) {
 			p_write(file->fd, buffer, read_bytes);
 			if (file->digest)
 				git_hash_update(file->digest, buffer, read_bytes);
 		}
 
 		p_close(source);
+
+		if (read_bytes < 0) {
+			giterr_set(GITERR_OS, "Failed to read file '%s'", file->path_original);
+			return -1;
+		}
 	}
 
 	return 0;

src/fileops.c

@@ -115,10 +115,33 @@ mode_t git_futils_canonical_mode(mode_t raw_mode)
 		return 0;
 }
 
-int git_futils_readbuffer_updated(git_buf *buf, const char *path, time_t *mtime, int *updated)
+int git_futils_readbuffer_fd(git_buf *buf, git_file fd, size_t len)
+{
+	ssize_t read_size;
+
+	git_buf_clear(buf);
+
+	if (git_buf_grow(buf, len + 1) < 0)
+		return -1;
+
+	/* p_read loops internally to read len bytes */
+	read_size = p_read(fd, buf->ptr, len);
+
+	if (read_size != (ssize_t)len) {
+		giterr_set(GITERR_OS, "Failed to read descriptor");
+		return -1;
+	}
+
+	buf->ptr[read_size] = '\0';
+	buf->size = read_size;
+
+	return 0;
+}
+
+int git_futils_readbuffer_updated(
+	git_buf *buf, const char *path, time_t *mtime, int *updated)
 {
 	git_file fd;
-	size_t len;
 	struct stat st;
 
 	assert(buf && path && *path);
@@ -147,30 +170,11 @@ int git_futils_readbuffer_updated(git_buf *buf, const char *path, time_t *mtime,
 	if (mtime != NULL)
 		*mtime = st.st_mtime;
 
-	len = (size_t) st.st_size;
-
-	git_buf_clear(buf);
-
-	if (git_buf_grow(buf, len + 1) < 0) {
+	if (git_futils_readbuffer_fd(buf, fd, (size_t)st.st_size) < 0) {
 		p_close(fd);
 		return -1;
 	}
 
-	buf->ptr[len] = '\0';
-
-	while (len > 0) {
-		ssize_t read_size = p_read(fd, buf->ptr, len);
-
-		if (read_size < 0) {
-			p_close(fd);
-			giterr_set(GITERR_OS, "Failed to read descriptor for '%s'", path);
-			return -1;
-		}
-
-		len -= read_size;
-		buf->size += read_size;
-	}
-
 	p_close(fd);
 
 	if (updated != NULL)

src/fileops.h

@@ -19,6 +19,7 @@
  */
 extern int git_futils_readbuffer(git_buf *obj, const char *path);
 extern int git_futils_readbuffer_updated(git_buf *obj, const char *path, time_t *mtime, int *updated);
+extern int git_futils_readbuffer_fd(git_buf *obj, git_file fd, size_t len);
 
 /**
  * File utils

src/object.c

@@ -77,6 +77,58 @@ static int create_object(git_object **object_out, git_otype type)
 	return 0;
 }
 
+int git_object__from_odb_object(
+	git_object **object_out,
+	git_repository *repo,
+	git_odb_object *odb_obj,
+	git_otype type)
+{
+	int error;
+	git_object *object = NULL;
+
+	if (type != GIT_OBJ_ANY && type != odb_obj->raw.type) {
+		giterr_set(GITERR_ODB, "The requested type does not match the type in the ODB");
+		return GIT_ENOTFOUND;
+	}
+
+	type = odb_obj->raw.type;
+
+	if ((error = create_object(&object, type)) < 0)
+		return error;
+
+	/* Initialize parent object */
+	git_oid_cpy(&object->cached.oid, &odb_obj->cached.oid);
+	object->repo = repo;
+
+	switch (type) {
+	case GIT_OBJ_COMMIT:
+		error = git_commit__parse((git_commit *)object, odb_obj);
+		break;
+
+	case GIT_OBJ_TREE:
+		error = git_tree__parse((git_tree *)object, odb_obj);
+		break;
+
+	case GIT_OBJ_TAG:
+		error = git_tag__parse((git_tag *)object, odb_obj);
+		break;
+
+	case GIT_OBJ_BLOB:
+		error = git_blob__parse((git_blob *)object, odb_obj);
+		break;
+
+	default:
+		break;
+	}
+
+	if (error < 0)
+		git_object__free(object);
+	else
+		*object_out = git_cache_try_store(&repo->objects, object);
+
+	return error;
+}
+
 int git_object_lookup_prefix(
 	git_object **object_out,
 	git_repository *repo,
@@ -148,53 +200,11 @@ int git_object_lookup_prefix(
 	if (error < 0)
 		return error;
 
-	if (type != GIT_OBJ_ANY && type != odb_obj->raw.type) {
-		git_odb_object_free(odb_obj);
-		giterr_set(GITERR_ODB, "The given type does not match the type on the ODB");
-		return GIT_ENOTFOUND;
-	}
-
-	type = odb_obj->raw.type;
-
-	if (create_object(&object, type) < 0) {
-		git_odb_object_free(odb_obj);
-		return -1;
-	}
-
-	/* Initialize parent object */
-	git_oid_cpy(&object->cached.oid, &odb_obj->cached.oid);
-	object->repo = repo;
-
-	switch (type) {
-	case GIT_OBJ_COMMIT:
-		error = git_commit__parse((git_commit *)object, odb_obj);
-		break;
-
-	case GIT_OBJ_TREE:
-		error = git_tree__parse((git_tree *)object, odb_obj);
-		break;
-
-	case GIT_OBJ_TAG:
-		error = git_tag__parse((git_tag *)object, odb_obj);
-		break;
-
-	case GIT_OBJ_BLOB:
-		error = git_blob__parse((git_blob *)object, odb_obj);
-		break;
-
-	default:
-		break;
-	}
+	error = git_object__from_odb_object(object_out, repo, odb_obj, type);
 
 	git_odb_object_free(odb_obj);
 
-	if (error < 0) {
-		git_object__free(object);
-		return -1;
-	}
-
-	*object_out = git_cache_try_store(&repo->objects, object);
-	return 0;
+	return error;
 }
 
 int git_object_lookup(git_object **object_out, git_repository *repo, const git_oid *id, git_otype type) {

src/object.h

+/*
+ * Copyright (C) 2009-2012 the libgit2 contributors
+ *
+ * This file is part of libgit2, distributed under the GNU GPL v2 with
+ * a Linking Exception. For full terms see the included COPYING file.
+ */
+#ifndef INCLUDE_object_h__
+#define INCLUDE_object_h__
+
+/** Base git object for inheritance */
+struct git_object {
+	git_cached_obj cached;
+	git_repository *repo;
+	git_otype type;
+};
+
+/* fully free the object; internal method, DO NOT EXPORT */
+void git_object__free(void *object);
+
+GIT_INLINE(int) git_object__dup(git_object **dest, git_object *source)
+{
+	git_cached_obj_incref(source);
+	*dest = source;
+	return 0;
+}
+
+int git_object__from_odb_object(
+	git_object **object_out,
+	git_repository *repo,
+	git_odb_object *odb_obj,
+	git_otype type);
+
+int git_object__resolve_to_type(git_object **obj, git_otype type);
+
+int git_oid__parse(git_oid *oid, const char **buffer_out, const char *buffer_end, const char *header);
+
+void git_oid__writebuf(git_buf *buf, const char *header, const git_oid *oid);
+
+#endif

src/odb.c

@@ -12,6 +12,7 @@
 #include "hash.h"
 #include "odb.h"
 #include "delta-apply.h"
+#include "filter.h"
 
 #include "git2/odb_backend.h"
 #include "git2/oid.h"
@@ -114,32 +115,62 @@ int git_odb__hashfd(git_oid *out, git_file fd, size_t size, git_otype type)
 	int hdr_len;
 	char hdr[64], buffer[2048];
 	git_hash_ctx *ctx;
+	ssize_t read_len;
 
 	hdr_len = format_object_header(hdr, sizeof(hdr), size, type);
 
 	ctx = git_hash_new_ctx();
+	GITERR_CHECK_ALLOC(ctx);
 
 	git_hash_update(ctx, hdr, hdr_len);
 
-	while (size > 0) {
-		ssize_t read_len = read(fd, buffer, sizeof(buffer));
-
-		if (read_len < 0) {
-			git_hash_free_ctx(ctx);
-			giterr_set(GITERR_OS, "Error reading file");
-			return -1;
-		}
-
+	while (size > 0 && (read_len = p_read(fd, buffer, sizeof(buffer))) > 0) {
 		git_hash_update(ctx, buffer, read_len);
 		size -= read_len;
 	}
 
+	/* If p_read returned an error code, the read obviously failed.
+	 * If size is not zero, the file was truncated after we originally
+	 * stat'd it, so we consider this a read failure too */
+	if (read_len < 0 || size > 0) {
+		git_hash_free_ctx(ctx);
+		giterr_set(GITERR_OS, "Error reading file for hashing");
+		return -1;
+	}
+
 	git_hash_final(out, ctx);
 	git_hash_free_ctx(ctx);
 
 	return 0;
 }
 
+int git_odb__hashfd_filtered(
+	git_oid *out, git_file fd, size_t size, git_otype type, git_vector *filters)
+{
+	int error;
+	git_buf raw = GIT_BUF_INIT;
+	git_buf filtered = GIT_BUF_INIT;
+
+	if (!filters || !filters->length)
+		return git_odb__hashfd(out, fd, size, type);
+
+	/* size of data is used in header, so we have to read the whole file
+	 * into memory to apply filters before beginning to calculate the hash
+	 */
+
+	if (!(error = git_futils_readbuffer_fd(&raw, fd, size)))
+		error = git_filters_apply(&filtered, &raw, filters);
+
+	git_buf_free(&raw);
+
+	if (!error)
+		error = git_odb_hash(out, filtered.ptr, filtered.size, type);
+
+	git_buf_free(&filtered);
+
+	return error;
+}
+
 int git_odb__hashlink(git_oid *out, const char *path)
 {
 	struct stat st;
@@ -171,7 +202,7 @@ int git_odb__hashlink(git_oid *out, const char *path)
 
 		result = git_odb_hash(out, link_data, (size_t)size, GIT_OBJ_BLOB);
 		git__free(link_data);
-	} else { 
+	} else {
 		int fd = git_futils_open_ro(path);
 		if (fd < 0)
 			return -1;
@@ -485,19 +516,36 @@ int git_odb_exists(git_odb *db, const git_oid *id)
 
 int git_odb_read_header(size_t *len_p, git_otype *type_p, git_odb *db, const git_oid *id)
 {
+	int error;
+	git_odb_object *object;
+
+	error = git_odb__read_header_or_object(&object, len_p, type_p, db, id);
+
+	if (object)
+		git_odb_object_free(object);
+
+	return error;
+}
+
+int git_odb__read_header_or_object(
+	git_odb_object **out, size_t *len_p, git_otype *type_p,
+	git_odb *db, const git_oid *id)
+{
 	unsigned int i;
 	int error = GIT_ENOTFOUND;
 	git_odb_object *object;
 
-	assert(db && id);
+	assert(db && id && out && len_p && type_p);
 
 	if ((object = git_cache_get(&db->cache, id)) != NULL) {
 		*len_p = object->raw.len;
 		*type_p = object->raw.type;
-		git_odb_object_free(object);
+		*out = object;
 		return 0;
 	}
 
+	*out = NULL;
+
 	for (i = 0; i < db->backends.length && error < 0; ++i) {
 		backend_internal *internal = git_vector_get(&db->backends, i);
 		git_odb_backend *b = internal->backend;
@@ -518,7 +566,8 @@ int git_odb_read_header(size_t *len_p, git_otype *type_p, git_odb *db, const git
 
 	*len_p = object->raw.len;
 	*type_p = object->raw.type;
-	git_odb_object_free(object);
+	*out = object;
+
 	return 0;
 }
 

src/odb.h

@@ -58,12 +58,19 @@ int git_odb__hashobj(git_oid *id, git_rawobj *obj);
 int git_odb__hashfd(git_oid *out, git_file fd, size_t size, git_otype type);
 
 /*
- * Hash a `path`, assuming it could be a POSIX symlink: if the path is a symlink,
- * then the raw contents of the symlink will be hashed. Otherwise, this will
- * fallback to `git_odb__hashfd`.
+ * Hash an open file descriptor applying an array of filters
+ * Acts just like git_odb__hashfd with the addition of filters...
+ */
+int git_odb__hashfd_filtered(
+	git_oid *out, git_file fd, size_t len, git_otype type, git_vector *filters);
+
+/*
+ * Hash a `path`, assuming it could be a POSIX symlink: if the path is a
+ * symlink, then the raw contents of the symlink will be hashed. Otherwise,
+ * this will fallback to `git_odb__hashfd`.
  *
- * The hash type for this call is always `GIT_OBJ_BLOB` because symlinks may only
- * point to blobs.
+ * The hash type for this call is always `GIT_OBJ_BLOB` because symlinks may
+ * only point to blobs.
  */
 int git_odb__hashlink(git_oid *out, const char *path);
 
@@ -77,4 +84,12 @@ int git_odb__error_notfound(const char *message, const git_oid *oid);
  */
 int git_odb__error_ambiguous(const char *message);
 
+/*
+ * Attempt to read object header or just return whole object if it could
+ * not be read.
+ */
+int git_odb__read_header_or_object(
+	git_odb_object **out, size_t *len_p, git_otype *type_p,
+	git_odb *db, const git_oid *id);
+
 #endif

src/repository.h

@@ -18,6 +18,7 @@
 #include "refs.h"
 #include "buffer.h"
 #include "odb.h"
+#include "object.h"
 #include "attr.h"
 #include "strmap.h"
 
@@ -75,13 +76,6 @@ enum {
 	GIT_REPOSITORY_INIT__IS_REINIT  = (1u << 18),
 };
 
-/** Base git object for inheritance */
-struct git_object {
-	git_cached_obj cached;
-	git_repository *repo;
-	git_otype type;
-};
-
 /** Internal structure for repository object */
 struct git_repository {
 	git_odb *_odb;
@@ -102,21 +96,6 @@ struct git_repository {
 	git_cvar_value cvar_cache[GIT_CVAR_CACHE_MAX];
 };
 
-/* fully free the object; internal method, DO NOT EXPORT */
-void git_object__free(void *object);
-
-GIT_INLINE(int) git_object__dup(git_object **dest, git_object *source)
-{
-	git_cached_obj_incref(source);
-	*dest = source;
-	return 0;
-}
-
-int git_object__resolve_to_type(git_object **obj, git_otype type);
-
-int git_oid__parse(git_oid *oid, const char **buffer_out, const char *buffer_end, const char *header);
-void git_oid__writebuf(git_buf *buf, const char *header, const git_oid *oid);
-
 GIT_INLINE(git_attr_cache *) git_repository_attr_cache(git_repository *repo)
 {
 	return &repo->attrcache;
@@ -136,7 +115,7 @@ int git_repository_odb__weakptr(git_odb **out, git_repository *repo);
 int git_repository_index__weakptr(git_index **out, git_repository *repo);
 
 /*
- * CVAR cache 
+ * CVAR cache
  *
  * Efficient access to the most used config variables of a repository.
  * The cache is cleared everytime the config backend is replaced.

tests-clar/diff/diff_helpers.c

@@ -89,7 +89,8 @@ int diff_line_fn(
 		e->line_adds++;
 		break;
 	case GIT_DIFF_LINE_ADD_EOFNL:
-		assert(0);
+		/* technically not a line add, but we'll count it as such */
+		e->line_adds++;
 		break;
 	case GIT_DIFF_LINE_DELETION:
 		e->line_dels++;
@@ -111,23 +112,21 @@ int diff_foreach_via_iterator(
 	git_diff_hunk_fn hunk_cb,
 	git_diff_data_fn line_cb)
 {
-	int error, curr, total;
+	int error;
 	git_diff_iterator *iter;
 	git_diff_delta *delta;
 
 	if ((error = git_diff_iterator_new(&iter, diff)) < 0)
 		return error;
 
-	curr  = 0;
-	total = git_diff_iterator_num_files(iter);
-
 	while (!(error = git_diff_iterator_next_file(&delta, iter))) {
 		git_diff_range *range;
 		const char *hdr;
 		size_t hdr_len;
+		float progress = git_diff_iterator_progress(iter);
 
 		/* call file_cb for this file */
-		if (file_cb != NULL && file_cb(data, delta, (float)curr / total) != 0)
+		if (file_cb != NULL && file_cb(data, delta, progress) != 0)
 			goto abort;
 
 		if (!hunk_cb && !line_cb)

tests-clar/diff/diffiter.c

@@ -114,3 +114,88 @@ void test_diff_diffiter__iterate_files_and_hunks(void)
 	git_diff_iterator_free(iter);
 	git_diff_list_free(diff);
 }
+
+void test_diff_diffiter__max_size_threshold(void)
+{
+	git_repository *repo = cl_git_sandbox_init("status");
+	git_diff_options opts = {0};
+	git_diff_list *diff = NULL;
+	git_diff_iterator *iter;
+	git_diff_delta *delta;
+	int error, file_count = 0, binary_count = 0, hunk_count = 0;
+
+	opts.context_lines = 3;
+	opts.interhunk_lines = 1;
+	opts.flags |= GIT_DIFF_INCLUDE_IGNORED | GIT_DIFF_INCLUDE_UNTRACKED;
+
+	cl_git_pass(git_diff_workdir_to_index(repo, &opts, &diff));
+	cl_git_pass(git_diff_iterator_new(&iter, diff));
+
+	while ((error = git_diff_iterator_next_file(&delta, iter)) != GIT_ITEROVER) {
+		cl_assert_equal_i(0, error);
+		cl_assert(delta);
+
+		file_count++;
+
+		hunk_count += git_diff_iterator_num_hunks_in_file(iter);
+
+		assert(delta->binary == 0 || delta->binary == 1);
+
+		binary_count += delta->binary;
+	}
+
+	cl_assert_equal_i(GIT_ITEROVER, error);
+	cl_assert(delta == NULL);
+
+	cl_assert_equal_i(13, file_count);
+	cl_assert_equal_i(0, binary_count);
+	cl_assert_equal_i(8, hunk_count);
+
+	git_diff_iterator_free(iter);
+	git_diff_list_free(diff);
+
+	/* try again with low file size threshold */
+
+	file_count = 0;
+	binary_count = 0;
+	hunk_count = 0;
+
+	opts.context_lines = 3;
+	opts.interhunk_lines = 1;
+	opts.flags |= GIT_DIFF_INCLUDE_IGNORED | GIT_DIFF_INCLUDE_UNTRACKED;
+	opts.max_size = 50; /* treat anything over 50 bytes as binary! */
+
+	cl_git_pass(git_diff_workdir_to_index(repo, &opts, &diff));
+	cl_git_pass(git_diff_iterator_new(&iter, diff));
+
+	while ((error = git_diff_iterator_next_file(&delta, iter)) != GIT_ITEROVER) {
+		cl_assert_equal_i(0, error);
+		cl_assert(delta);
+
+		file_count++;
+
+		hunk_count += git_diff_iterator_num_hunks_in_file(iter);
+
+		assert(delta->binary == 0 || delta->binary == 1);
+
+		binary_count += delta->binary;
+	}
+
+	cl_assert_equal_i(GIT_ITEROVER, error);
+	cl_assert(delta == NULL);
+
+	cl_assert_equal_i(13, file_count);
+
+	/* Three files are over the 50 byte threshold:
+	 * - staged_changes_file_deleted
+	 * - staged_changes_modified_file
+	 * - staged_new_file_modified_file
+	 */
+	cl_assert_equal_i(3, binary_count);
+
+	cl_assert_equal_i(5, hunk_count);
+
+	git_diff_iterator_free(iter);
+	git_diff_list_free(diff);
+
+}

tests-clar/status/worktree.c

@@ -797,3 +797,47 @@ void test_status_worktree__interruptable_foreach(void)
 
 	cl_assert_equal_i(8, count);
 }
+
+void test_status_worktree__new_staged_file_must_handle_crlf(void)
+{
+	git_repository *repo;
+	git_index *index;
+	git_config *config;
+	unsigned int status;
+
+	cl_git_pass(git_repository_init(&repo, "getting_started", 0));
+
+	// Ensure that repo has core.autocrlf=true
+	cl_git_pass(git_repository_config(&config, repo));
+	cl_git_pass(git_config_set_bool(config, "core.autocrlf", true));
+
+	cl_git_mkfile("getting_started/testfile.txt", "content\r\n");	// Content with CRLF
+
+	cl_git_pass(git_repository_index(&index, repo));
+	cl_git_pass(git_index_add(index, "testfile.txt", 0));
+	cl_git_pass(git_index_write(index));
+
+	cl_git_pass(git_status_file(&status, repo, "testfile.txt"));
+	cl_assert_equal_i(GIT_STATUS_INDEX_NEW, status);
+
+	git_config_free(config);
+	git_index_free(index);
+	git_repository_free(repo);
+}
+
+void test_status_worktree__line_endings_dont_count_as_changes_with_autocrlf(void)
+{
+	git_repository *repo = cl_git_sandbox_init("status");
+	git_config *config;
+	unsigned int status;
+
+	cl_git_pass(git_repository_config(&config, repo));
+	cl_git_pass(git_config_set_bool(config, "core.autocrlf", true));
+	git_config_free(config);
+
+	cl_git_rewritefile("status/current_file", "current_file\r\n");
+
+	cl_git_pass(git_status_file(&status, repo, "current_file"));
+
+	cl_assert_equal_i(GIT_STATUS_CURRENT, status);
+}