config: introduce an optional event stream while parsing

This extends our config parser so that it can optionally produce an event
stream via callback function, where it reports e.g. when a comment was
parsed, or a section header, etc.

This parser will be used subsequently to handle the scenarios better where
removing config entries would make sections empty, or where a new entry
could be added to an already-existing, empty section.

Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/config.c b/config.c
index c55d6a564e256b56e8f3f41feac2e0045936d1e1..d53ed88281d6c65cb69262939455b9aafbe0c290 100644 (file)
--- a/config.c
+++ b/config.c
@@ -653,7 +653,45 @@ static int get_base_var(struct strbuf *name)
        }
 }
 
        }
 }
 

-static int git_parse_source(config_fn_t fn, void *data)
+struct parse_event_data {
+       enum config_event_t previous_type;
+       size_t previous_offset;
+       const struct config_options *opts;
+};
+
+static int do_event(enum config_event_t type, struct parse_event_data *data)
+{
+       size_t offset;
+
+       if (!data->opts || !data->opts->event_fn)
+               return 0;
+
+       if (type == CONFIG_EVENT_WHITESPACE &&
+           data->previous_type == type)
+               return 0;
+
+       offset = cf->do_ftell(cf);
+       /*
+        * At EOF, the parser always "inserts" an extra '\n', therefore
+        * the end offset of the event is the current file position, otherwise
+        * we will already have advanced to the next event.
+        */
+       if (type != CONFIG_EVENT_EOF)
+               offset--;
+
+       if (data->previous_type != CONFIG_EVENT_EOF &&
+           data->opts->event_fn(data->previous_type, data->previous_offset,
+                                offset, data->opts->event_fn_data) < 0)
+               return -1;
+
+       data->previous_type = type;
+       data->previous_offset = offset;
+
+       return 0;
+}
+
+static int git_parse_source(config_fn_t fn, void *data,
+                           const struct config_options *opts)

 {
        int comment = 0;
        int baselen = 0;
 {
        int comment = 0;
        int baselen = 0;


@@ -664,8 +702,15 @@ static int git_parse_source(config_fn_t fn, void *data)
        /* U+FEFF Byte Order Mark in UTF8 */
        const char *bomptr = utf8_bom;
 
        /* U+FEFF Byte Order Mark in UTF8 */
        const char *bomptr = utf8_bom;
 

+       /* For the parser event callback */
+       struct parse_event_data event_data = {
+               CONFIG_EVENT_EOF, 0, opts
+       };
+

        for (;;) {
        for (;;) {

-               int c = get_next_char();
+               int c;
+
+               c = get_next_char();

                if (bomptr && *bomptr) {
                        /* We are at the file beginning; skip UTF8-encoded BOM
                         * if present. Sane editors won't put this in on their
                if (bomptr && *bomptr) {
                        /* We are at the file beginning; skip UTF8-encoded BOM
                         * if present. Sane editors won't put this in on their


@@ -682,18 +727,33 @@ static int git_parse_source(config_fn_t fn, void *data)
                        }
                }
                if (c == '\n') {
                        }
                }
                if (c == '\n') {

-                       if (cf->eof)
+                       if (cf->eof) {
+                               if (do_event(CONFIG_EVENT_EOF, &event_data) < 0)
+                                       return -1;

                                return 0;
                                return 0;

+                       }
+                       if (do_event(CONFIG_EVENT_WHITESPACE, &event_data) < 0)
+                               return -1;

                        comment = 0;
                        continue;
                }
                        comment = 0;
                        continue;
                }

-               if (comment || isspace(c))
+               if (comment)

                        continue;
                        continue;

+               if (isspace(c)) {
+                       if (do_event(CONFIG_EVENT_WHITESPACE, &event_data) < 0)
+                                       return -1;
+                       continue;
+               }

                if (c == '#' || c == ';') {
                if (c == '#' || c == ';') {

+                       if (do_event(CONFIG_EVENT_COMMENT, &event_data) < 0)
+                                       return -1;

                        comment = 1;
                        continue;
                }
                if (c == '[') {
                        comment = 1;
                        continue;
                }
                if (c == '[') {

+                       if (do_event(CONFIG_EVENT_SECTION, &event_data) < 0)
+                                       return -1;
+

                        /* Reset prior to determining a new stem */
                        strbuf_reset(var);
                        if (get_base_var(var) < 0 || var->len < 1)
                        /* Reset prior to determining a new stem */
                        strbuf_reset(var);
                        if (get_base_var(var) < 0 || var->len < 1)


@@ -704,6 +764,10 @@ static int git_parse_source(config_fn_t fn, void *data)
                }
                if (!isalpha(c))
                        break;
                }
                if (!isalpha(c))
                        break;

+
+               if (do_event(CONFIG_EVENT_ENTRY, &event_data) < 0)
+                       return -1;
+

                /*
                 * Truncate the var name back to the section header
                 * stem prior to grabbing the suffix part of the name
                /*
                 * Truncate the var name back to the section header
                 * stem prior to grabbing the suffix part of the name


@@ -715,6 +779,9 @@ static int git_parse_source(config_fn_t fn, void *data)
                        break;
        }
 
                        break;
        }
 

+       if (do_event(CONFIG_EVENT_ERROR, &event_data) < 0)
+               return -1;
+

        switch (cf->origin_type) {
        case CONFIG_ORIGIN_BLOB:
                error_msg = xstrfmt(_("bad config line %d in blob %s"),
        switch (cf->origin_type) {
        case CONFIG_ORIGIN_BLOB:
                error_msg = xstrfmt(_("bad config line %d in blob %s"),


@@ -1390,7 +1457,8 @@ int git_default_config(const char *var, const char *value, void *dummy)
  * fgetc, ungetc, ftell of top need to be initialized before calling
  * this function.
  */
  * fgetc, ungetc, ftell of top need to be initialized before calling
  * this function.
  */

-static int do_config_from(struct config_source *top, config_fn_t fn, void *data)
+static int do_config_from(struct config_source *top, config_fn_t fn, void *data,
+                         const struct config_options *opts)

 {
        int ret;
 
 {
        int ret;
 


@@ -1402,7 +1470,7 @@ static int do_config_from(struct config_source *top, config_fn_t fn, void *data)
        strbuf_init(&top->var, 1024);
        cf = top;
 
        strbuf_init(&top->var, 1024);
        cf = top;
 

-       ret = git_parse_source(fn, data);
+       ret = git_parse_source(fn, data, opts);

 
        /* pop config-file parsing state stack */
        strbuf_release(&top->value);
 
        /* pop config-file parsing state stack */
        strbuf_release(&top->value);


@@ -1415,7 +1483,7 @@ static int do_config_from(struct config_source *top, config_fn_t fn, void *data)
 static int do_config_from_file(config_fn_t fn,
                const enum config_origin_type origin_type,
                const char *name, const char *path, FILE *f,
 static int do_config_from_file(config_fn_t fn,
                const enum config_origin_type origin_type,
                const char *name, const char *path, FILE *f,

-               void *data)
+               void *data, const struct config_options *opts)

 {
        struct config_source top;
 
 {
        struct config_source top;
 


@@ -1428,15 +1496,18 @@ static int do_config_from_file(config_fn_t fn,
        top.do_ungetc = config_file_ungetc;
        top.do_ftell = config_file_ftell;
 
        top.do_ungetc = config_file_ungetc;
        top.do_ftell = config_file_ftell;
 

-       return do_config_from(&top, fn, data);
+       return do_config_from(&top, fn, data, opts);

 }
 
 static int git_config_from_stdin(config_fn_t fn, void *data)
 {
 }
 
 static int git_config_from_stdin(config_fn_t fn, void *data)
 {

-       return do_config_from_file(fn, CONFIG_ORIGIN_STDIN, "", NULL, stdin, data);
+       return do_config_from_file(fn, CONFIG_ORIGIN_STDIN, "", NULL, stdin,
+                                  data, NULL);

 }
 
 }
 

-int git_config_from_file(config_fn_t fn, const char *filename, void *data)
+int git_config_from_file_with_options(config_fn_t fn, const char *filename,
+                                     void *data,
+                                     const struct config_options *opts)

 {
        int ret = -1;
        FILE *f;
 {
        int ret = -1;
        FILE *f;


@@ -1444,13 +1515,19 @@ int git_config_from_file(config_fn_t fn, const char *filename, void *data)
        f = fopen_or_warn(filename, "r");
        if (f) {
                flockfile(f);
        f = fopen_or_warn(filename, "r");
        if (f) {
                flockfile(f);

-               ret = do_config_from_file(fn, CONFIG_ORIGIN_FILE, filename, filename, f, data);
+               ret = do_config_from_file(fn, CONFIG_ORIGIN_FILE, filename,
+                                         filename, f, data, opts);

                funlockfile(f);
                fclose(f);
        }
        return ret;
 }
 
                funlockfile(f);
                fclose(f);
        }
        return ret;
 }
 

+int git_config_from_file(config_fn_t fn, const char *filename, void *data)
+{
+       return git_config_from_file_with_options(fn, filename, data, NULL);
+}
+

 int git_config_from_mem(config_fn_t fn, const enum config_origin_type origin_type,
                        const char *name, const char *buf, size_t len, void *data)
 {
 int git_config_from_mem(config_fn_t fn, const enum config_origin_type origin_type,
                        const char *name, const char *buf, size_t len, void *data)
 {


@@ -1467,7 +1544,7 @@ int git_config_from_mem(config_fn_t fn, const enum config_origin_type origin_typ
        top.do_ungetc = config_buf_ungetc;
        top.do_ftell = config_buf_ftell;
 
        top.do_ungetc = config_buf_ungetc;
        top.do_ftell = config_buf_ftell;
 

-       return do_config_from(&top, fn, data);
+       return do_config_from(&top, fn, data, NULL);

 }
 
 int git_config_from_blob_oid(config_fn_t fn,
 }
 
 int git_config_from_blob_oid(config_fn_t fn,

diff --git a/config.h b/config.h
index ef70a9cac1e6dc67df24d157a4e5de38edd8c984..5a2394daae21d68ad0e44f6ec47ccac9afb6284a 100644 (file)
--- a/config.h
+++ b/config.h
@@ -28,15 +28,40 @@ enum config_origin_type {
        CONFIG_ORIGIN_CMDLINE
 };
 
        CONFIG_ORIGIN_CMDLINE
 };
 

+enum config_event_t {
+       CONFIG_EVENT_SECTION,
+       CONFIG_EVENT_ENTRY,
+       CONFIG_EVENT_WHITESPACE,
+       CONFIG_EVENT_COMMENT,
+       CONFIG_EVENT_EOF,
+       CONFIG_EVENT_ERROR
+};
+
+/*
+ * The parser event function (if not NULL) is called with the event type and
+ * the begin/end offsets of the parsed elements.
+ *
+ * Note: for CONFIG_EVENT_ENTRY (i.e. config variables), the trailing newline
+ * character is considered part of the element.
+ */
+typedef int (*config_parser_event_fn_t)(enum config_event_t type,
+                                       size_t begin_offset, size_t end_offset,
+                                       void *event_fn_data);
+

 struct config_options {
        unsigned int respect_includes : 1;
        const char *commondir;
        const char *git_dir;
 struct config_options {
        unsigned int respect_includes : 1;
        const char *commondir;
        const char *git_dir;

+       config_parser_event_fn_t event_fn;
+       void *event_fn_data;

 };
 
 typedef int (*config_fn_t)(const char *, const char *, void *);
 extern int git_default_config(const char *, const char *, void *);
 extern int git_config_from_file(config_fn_t fn, const char *, void *);
 };
 
 typedef int (*config_fn_t)(const char *, const char *, void *);
 extern int git_default_config(const char *, const char *, void *);
 extern int git_config_from_file(config_fn_t fn, const char *, void *);

+extern int git_config_from_file_with_options(config_fn_t fn, const char *,
+                                            void *,
+                                            const struct config_options *);

 extern int git_config_from_mem(config_fn_t fn, const enum config_origin_type,
                                        const char *name, const char *buf, size_t len, void *data);
 extern int git_config_from_blob_oid(config_fn_t fn, const char *name,
 extern int git_config_from_mem(config_fn_t fn, const enum config_origin_type,
                                        const char *name, const char *buf, size_t len, void *data);
 extern int git_config_from_blob_oid(config_fn_t fn, const char *name,