Improve changelog handling through addition of open/read/close functions

Thanks to Allan for inspiring all this work on what was one little TODO item
in the codebase. :)

Change changelog handling so we can now dump a changelog from both installed
packages and package files (fixes FS#7371). We do this by moving all of the
machinery to the backend where it should have been in the first place.

The changelog reading is now done through a open/read/close interface
similar to the fopen/fread/fclose functions (can you guess how it is done?).
It is buffered by the frontend, so programs using the library can read as
much or as little as they want at a time.

Unfortunately, I could not implement a changelog_feof function due to some
shortcomings of libarchive. However, I left the stub code in there,
commented out, in case it becomes possible later or anyone wants to take a
stab at it.

Original-work-by: Allan McRae <mcrae_allan@hotmail.com>
Improved-by: Chantry Xavier <shiningxc@gmail.com>
Signed-off-by: Dan McGee <dan@archlinux.org>

lib/libalpm/alpm.h

@@ -216,6 +216,11 @@ alpm_list_t *alpm_pkg_get_deltas(pmpkg_t *pkg);
 alpm_list_t *alpm_pkg_get_replaces(pmpkg_t *pkg);
 alpm_list_t *alpm_pkg_get_files(pmpkg_t *pkg);
 alpm_list_t *alpm_pkg_get_backup(pmpkg_t *pkg);
+void *alpm_pkg_changelog_open(pmpkg_t *pkg);
+size_t alpm_pkg_changelog_read(void *ptr, size_t size,
+		const pmpkg_t *pkg, const void *fp);
+/*int alpm_pkg_changelog_feof(const pmpkg_t *pkg, void *fp);*/
+int alpm_pkg_changelog_close(const pmpkg_t *pkg, void *fp);
 unsigned short alpm_pkg_has_scriptlet(pmpkg_t *pkg);
 
 unsigned long alpm_pkg_download_size(pmpkg_t *newpkg, pmdb_t *db_local);

lib/libalpm/package.c

@@ -491,6 +491,115 @@ alpm_list_t SYMEXPORT *alpm_pkg_get_backup(pmpkg_t *pkg)
 	return pkg->backup;
 }
 
+/**
+ * Open a package changelog for reading. Similar to fopen in functionality,
+ * except that the returned 'file stream' could really be from an archive
+ * as well as from the database.
+ * @param pkg the package to read the changelog of (either file or db)
+ * @return a 'file stream' to the package changelog
+ */
+void SYMEXPORT *alpm_pkg_changelog_open(pmpkg_t *pkg)
+{
+	ALPM_LOG_FUNC;
+
+	/* Sanity checks */
+	ASSERT(handle != NULL, return(NULL));
+	ASSERT(pkg != NULL, return(NULL));
+
+	if(pkg->origin == PKG_FROM_CACHE) {
+		char clfile[PATH_MAX];
+		snprintf(clfile, PATH_MAX, "%s/%s/%s-%s/changelog",
+				alpm_option_get_dbpath(),
+				alpm_db_get_name(handle->db_local),
+				alpm_pkg_get_name(pkg),
+				alpm_pkg_get_version(pkg));
+		return fopen(clfile, "r");
+	} else if(pkg->origin == PKG_FROM_FILE) {
+		struct archive *archive = NULL;
+		struct archive_entry *entry;
+		const char *pkgfile = pkg->origin_data.file;
+		int ret = ARCHIVE_OK;
+
+		if((archive = archive_read_new()) == NULL) {
+			RET_ERR(PM_ERR_LIBARCHIVE_ERROR, NULL);
+		}
+
+		archive_read_support_compression_all(archive);
+		archive_read_support_format_all(archive);
+
+		if (archive_read_open_filename(archive, pkgfile,
+					ARCHIVE_DEFAULT_BYTES_PER_BLOCK) != ARCHIVE_OK) {
+			RET_ERR(PM_ERR_PKG_OPEN, NULL);
+		}
+
+		while((ret = archive_read_next_header(archive, &entry)) == ARCHIVE_OK) {
+			const char *entry_name = archive_entry_pathname(entry);
+
+			if(strcmp(entry_name, ".CHANGELOG") == 0) {
+				return(archive);
+			}
+		}
+		/* we didn't find a changelog */
+		archive_read_finish(archive);
+		errno = ENOENT;
+	}
+	return(NULL);
+}
+
+/**
+ * Read data from an open changelog 'file stream'. Similar to fread in
+ * functionality, this function takes a buffer and amount of data to read.
+ * @param ptr a buffer to fill with raw changelog data
+ * @param size the size of the buffer
+ * @param pkg the package that the changelog is being read from
+ * @param fp a 'file stream' to the package changelog
+ * @return the number of characters read, or 0 if there is no more data
+ */
+size_t SYMEXPORT alpm_pkg_changelog_read(void *ptr, size_t size,
+		const pmpkg_t *pkg, const void *fp)
+{
+	size_t ret = 0;
+	if(pkg->origin == PKG_FROM_CACHE) {
+		ret = fread(ptr, 1, size, (FILE*)fp);
+	} else if(pkg->origin == PKG_FROM_FILE) {
+		ret = archive_read_data((struct archive*)fp, ptr, size);
+	}
+	return(ret);
+}
+
+/*
+int SYMEXPORT alpm_pkg_changelog_feof(const pmpkg_t *pkg, void *fp)
+{
+	int ret = 0;
+	if(pkg->origin == PKG_FROM_CACHE) {
+		ret = feof((FILE*)fp);
+	} else if(pkg->origin == PKG_FROM_FILE) {
+		// note: this doesn't quite work, no feof in libarchive
+		ret = archive_read_data((struct archive*)fp, NULL, 0);
+	}
+	return(ret);
+}
+*/
+
+/**
+ * Close a package changelog for reading. Similar to fclose in functionality,
+ * except that the 'file stream' could really be from an archive as well as
+ * from the database.
+ * @param pkg the package that the changelog was read from
+ * @param fp a 'file stream' to the package changelog
+ * @return whether closing the package changelog stream was successful
+ */
+int SYMEXPORT alpm_pkg_changelog_close(const pmpkg_t *pkg, void *fp)
+{
+	int ret = 0;
+	if(pkg->origin == PKG_FROM_CACHE) {
+		ret = fclose((FILE*)fp);
+	} else if(pkg->origin == PKG_FROM_FILE) {
+		ret = archive_read_finish((struct archive *)fp);
+	}
+	return(ret);
+}
+
 unsigned short SYMEXPORT alpm_pkg_has_scriptlet(pmpkg_t *pkg)
 {
 	ALPM_LOG_FUNC;

src/pacman/package.c

@@ -34,6 +34,8 @@
 #include "package.h"
 #include "util.h"
 
+#define CLBUF_SIZE 4096
+
 /* Display the content of a package
  *
  * level: <0 - sync package [-Si]
@@ -232,28 +234,30 @@ void dump_pkg_files(pmpkg_t *pkg)
 	fflush(stdout);
 }
 
-/* Display the changelog of an installed package
+/* Display the changelog of a package
  */
-void dump_pkg_changelog(char *clfile, const char *pkgname)
+void dump_pkg_changelog(pmpkg_t *pkg)
 {
-	FILE* fp = NULL;
-	char line[PATH_MAX+1];
+	void *fp = NULL;
 
-	if((fp = fopen(clfile, "r")) == NULL)
-	{
-		fprintf(stderr, _("error: no changelog available for '%s'.\n"), pkgname);
+	if((fp = alpm_pkg_changelog_open(pkg)) == NULL) {
+		/* TODO after string freeze use pm_fprintf */
+		fprintf(stderr, _("error: no changelog available for '%s'.\n"),
+				alpm_pkg_get_name(pkg));
 		return;
-	}
-	else
-	{
-		while(!feof(fp))
-		{
-			fgets(line, (int)PATH_MAX, fp);
-			printf("%s", line);
-			line[0] = '\0';
+	} else {
+		/* allocate a buffer to get the changelog back in chunks */
+		char buf[CLBUF_SIZE];
+		int ret = 0;
+		while((ret = alpm_pkg_changelog_read(buf, CLBUF_SIZE, pkg, fp))) {
+			if(ret < CLBUF_SIZE) {
+				/* if we hit the end of the file, we need to add a null terminator */
+				*(buf + ret) = '\0';
+			}
+			printf("%s", buf);
 		}
-		fclose(fp);
-		return;
+		alpm_pkg_changelog_close(pkg, fp);
+		printf("\n");
 	}
 }
 

src/pacman/package.h

@@ -28,7 +28,7 @@ void dump_pkg_sync(pmpkg_t *pkg, const char *treename);
 
 void dump_pkg_backups(pmpkg_t *pkg);
 void dump_pkg_files(pmpkg_t *pkg);
-void dump_pkg_changelog(char *clfile, const char *pkgname);
+void dump_pkg_changelog(pmpkg_t *pkg);
 
 #endif /* _PM_PACKAGE_H */
 

src/pacman/query.c

@@ -312,14 +312,7 @@ static void display(pmpkg_t *pkg)
 		dump_pkg_files(pkg);
 	}
 	if(config->op_q_changelog) {
-		char changelog[PATH_MAX];
-		/* TODO should be done in the backend- no raw DB stuff up front */
-		snprintf(changelog, PATH_MAX, "%s/%s/%s-%s/changelog",
-				alpm_option_get_dbpath(),
-				alpm_db_get_name(db_local),
-				alpm_pkg_get_name(pkg),
-				alpm_pkg_get_version(pkg));
-		dump_pkg_changelog(changelog, alpm_pkg_get_name(pkg));
+		dump_pkg_changelog(pkg);
 	}
 	if(!config->op_q_info && !config->op_q_list && !config->op_q_changelog) {
 		if (!config->quiet) {