From 28224c23597e5d4b405b87e4e3dc321fd2d2c4f6 Mon Sep 17 00:00:00 2001 From: Phillip Wood Date: Wed, 31 Oct 2018 10:15:52 +0000 Subject: am: don't die in read_author_script() The caller is already prepared to handle errors returned from this function so there is no need for it to die if it cannot read the file. Suggested-by: Eric Sunshine Signed-off-by: Phillip Wood Signed-off-by: Junio C Hamano --- builtin/am.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/builtin/am.c b/builtin/am.c index 5e643e2a3e..4f7f28a9dc 100644 --- a/builtin/am.c +++ b/builtin/am.c @@ -318,7 +318,8 @@ static int read_author_script(struct am_state *state) if (fd < 0) { if (errno == ENOENT) return 0; - die_errno(_("could not open '%s' for reading"), filename); + return error_errno(_("could not open '%s' for reading"), + filename); } strbuf_read(&buf, fd, 0); close(fd); -- cgit v1.2.3 From 442c36bd08a283b158995fd75d340e6981b80e34 Mon Sep 17 00:00:00 2001 From: Phillip Wood Date: Wed, 31 Oct 2018 10:15:53 +0000 Subject: am: improve author-script error reporting If there are errors in a user edited author-script there was no indication of what was wrong. This commit adds some specific error messages depending on the problem. It also relaxes the requirement that the variables appear in a specific order in the file to match the behavior of 'rebase --interactive'. Signed-off-by: Phillip Wood Signed-off-by: Junio C Hamano --- builtin/am.c | 49 +++++++++++++++++++++++++++++++++++++++---------- 1 file changed, 39 insertions(+), 10 deletions(-) diff --git a/builtin/am.c b/builtin/am.c index 4f7f28a9dc..ffca4479d7 100644 --- a/builtin/am.c +++ b/builtin/am.c @@ -270,8 +270,11 @@ static int parse_key_value_squoted(char *buf, struct string_list *list) struct string_list_item *item; char *np; char *cp = strchr(buf, '='); - if (!cp) - return -1; + if (!cp) { + np = strchrnul(buf, '\n'); + return error(_("unable to parse '%.*s'"), + (int) (np - buf), buf); + } np = strchrnul(cp, '\n'); *cp++ = '\0'; item = string_list_append(list, buf); @@ -280,7 +283,8 @@ static int parse_key_value_squoted(char *buf, struct string_list *list) *np = '\0'; cp = sq_dequote(cp); if (!cp) - return -1; + return error(_("unable to dequote value of '%s'"), + item->string); item->util = xstrdup(cp); } return 0; @@ -308,6 +312,7 @@ static int read_author_script(struct am_state *state) struct strbuf buf = STRBUF_INIT; struct string_list kv = STRING_LIST_INIT_DUP; int retval = -1; /* assume failure */ + int i, name_i = -2, email_i = -2, date_i = -2, err = 0; int fd; assert(!state->author_name); @@ -326,14 +331,38 @@ static int read_author_script(struct am_state *state) if (parse_key_value_squoted(buf.buf, &kv)) goto finish; - if (kv.nr != 3 || - strcmp(kv.items[0].string, "GIT_AUTHOR_NAME") || - strcmp(kv.items[1].string, "GIT_AUTHOR_EMAIL") || - strcmp(kv.items[2].string, "GIT_AUTHOR_DATE")) + for (i = 0; i < kv.nr; i++) { + if (!strcmp(kv.items[i].string, "GIT_AUTHOR_NAME")) { + if (name_i != -2) + name_i = error(_("'GIT_AUTHOR_NAME' already given")); + else + name_i = i; + } else if (!strcmp(kv.items[i].string, "GIT_AUTHOR_EMAIL")) { + if (email_i != -2) + email_i = error(_("'GIT_AUTHOR_EMAIL' already given")); + else + email_i = i; + } else if (!strcmp(kv.items[i].string, "GIT_AUTHOR_DATE")) { + if (date_i != -2) + date_i = error(_("'GIT_AUTHOR_DATE' already given")); + else + date_i = i; + } else { + err = error(_("unknown variable '%s'"), + kv.items[i].string); + } + } + if (name_i == -2) + error(_("missing 'GIT_AUTHOR_NAME'")); + if (email_i == -2) + error(_("missing 'GIT_AUTHOR_EMAIL'")); + if (date_i == -2) + error(_("missing 'GIT_AUTHOR_DATE'")); + if (date_i < 0 || email_i < 0 || date_i < 0 || err) goto finish; - state->author_name = kv.items[0].util; - state->author_email = kv.items[1].util; - state->author_date = kv.items[2].util; + state->author_name = kv.items[name_i].util; + state->author_email = kv.items[email_i].util; + state->author_date = kv.items[date_i].util; retval = 0; finish: string_list_clear(&kv, !!retval); -- cgit v1.2.3 From a75d35138850e3a171243c5fafce4efe75827e06 Mon Sep 17 00:00:00 2001 From: Phillip Wood Date: Wed, 31 Oct 2018 10:15:54 +0000 Subject: am: rename read_author_script() Rename read_author_script() in preparation for adding a shared read_author_script() function to libgit. Signed-off-by: Phillip Wood Signed-off-by: Junio C Hamano --- builtin/am.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/builtin/am.c b/builtin/am.c index ffca4479d7..c78a745289 100644 --- a/builtin/am.c +++ b/builtin/am.c @@ -306,7 +306,7 @@ static int parse_key_value_squoted(char *buf, struct string_list *list) * script, and thus if the file differs from what this function expects, it is * better to bail out than to do something that the user does not expect. */ -static int read_author_script(struct am_state *state) +static int read_am_author_script(struct am_state *state) { const char *filename = am_path(state, "author-script"); struct strbuf buf = STRBUF_INIT; @@ -441,7 +441,7 @@ static void am_load(struct am_state *state) BUG("state file 'last' does not exist"); state->last = strtol(sb.buf, NULL, 10); - if (read_author_script(state) < 0) + if (read_am_author_script(state) < 0) die(_("could not parse author script")); read_commit_msg(state); -- cgit v1.2.3 From bcd33ec25f28514776f3b17af6a5a80b1f329f81 Mon Sep 17 00:00:00 2001 From: Phillip Wood Date: Wed, 31 Oct 2018 10:15:55 +0000 Subject: add read_author_script() to libgit Add read_author_script() to sequencer.c based on the implementation in builtin/am.c and update read_am_author_script() to use read_author_script(). The sequencer code that reads the author script will be updated in the next commit. Signed-off-by: Phillip Wood Signed-off-by: Junio C Hamano --- builtin/am.c | 86 ++---------------------------------------------- sequencer.c | 105 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ sequencer.h | 3 ++ 3 files changed, 110 insertions(+), 84 deletions(-) diff --git a/builtin/am.c b/builtin/am.c index c78a745289..83685180e0 100644 --- a/builtin/am.c +++ b/builtin/am.c @@ -260,36 +260,6 @@ static int read_state_file(struct strbuf *sb, const struct am_state *state, die_errno(_("could not read '%s'"), am_path(state, file)); } -/** - * Take a series of KEY='VALUE' lines where VALUE part is - * sq-quoted, and append at the end of the string list - */ -static int parse_key_value_squoted(char *buf, struct string_list *list) -{ - while (*buf) { - struct string_list_item *item; - char *np; - char *cp = strchr(buf, '='); - if (!cp) { - np = strchrnul(buf, '\n'); - return error(_("unable to parse '%.*s'"), - (int) (np - buf), buf); - } - np = strchrnul(cp, '\n'); - *cp++ = '\0'; - item = string_list_append(list, buf); - - buf = np + (*np == '\n'); - *np = '\0'; - cp = sq_dequote(cp); - if (!cp) - return error(_("unable to dequote value of '%s'"), - item->string); - item->util = xstrdup(cp); - } - return 0; -} - /** * Reads and parses the state directory's "author-script" file, and sets * state->author_name, state->author_email and state->author_date accordingly. @@ -309,65 +279,13 @@ static int parse_key_value_squoted(char *buf, struct string_list *list) static int read_am_author_script(struct am_state *state) { const char *filename = am_path(state, "author-script"); - struct strbuf buf = STRBUF_INIT; - struct string_list kv = STRING_LIST_INIT_DUP; - int retval = -1; /* assume failure */ - int i, name_i = -2, email_i = -2, date_i = -2, err = 0; - int fd; assert(!state->author_name); assert(!state->author_email); assert(!state->author_date); - fd = open(filename, O_RDONLY); - if (fd < 0) { - if (errno == ENOENT) - return 0; - return error_errno(_("could not open '%s' for reading"), - filename); - } - strbuf_read(&buf, fd, 0); - close(fd); - if (parse_key_value_squoted(buf.buf, &kv)) - goto finish; - - for (i = 0; i < kv.nr; i++) { - if (!strcmp(kv.items[i].string, "GIT_AUTHOR_NAME")) { - if (name_i != -2) - name_i = error(_("'GIT_AUTHOR_NAME' already given")); - else - name_i = i; - } else if (!strcmp(kv.items[i].string, "GIT_AUTHOR_EMAIL")) { - if (email_i != -2) - email_i = error(_("'GIT_AUTHOR_EMAIL' already given")); - else - email_i = i; - } else if (!strcmp(kv.items[i].string, "GIT_AUTHOR_DATE")) { - if (date_i != -2) - date_i = error(_("'GIT_AUTHOR_DATE' already given")); - else - date_i = i; - } else { - err = error(_("unknown variable '%s'"), - kv.items[i].string); - } - } - if (name_i == -2) - error(_("missing 'GIT_AUTHOR_NAME'")); - if (email_i == -2) - error(_("missing 'GIT_AUTHOR_EMAIL'")); - if (date_i == -2) - error(_("missing 'GIT_AUTHOR_DATE'")); - if (date_i < 0 || email_i < 0 || date_i < 0 || err) - goto finish; - state->author_name = kv.items[name_i].util; - state->author_email = kv.items[email_i].util; - state->author_date = kv.items[date_i].util; - retval = 0; -finish: - string_list_clear(&kv, !!retval); - strbuf_release(&buf); - return retval; + return read_author_script(filename, &state->author_name, + &state->author_email, &state->author_date, 1); } /** diff --git a/sequencer.c b/sequencer.c index 6387c9ee6e..bf84a4f8ea 100644 --- a/sequencer.c +++ b/sequencer.c @@ -664,6 +664,111 @@ missing_author: return res; } +/** + * Take a series of KEY='VALUE' lines where VALUE part is + * sq-quoted, and append at the end of the string list + */ +static int parse_key_value_squoted(char *buf, struct string_list *list) +{ + while (*buf) { + struct string_list_item *item; + char *np; + char *cp = strchr(buf, '='); + if (!cp) { + np = strchrnul(buf, '\n'); + return error(_("no key present in '%.*s'"), + (int) (np - buf), buf); + } + np = strchrnul(cp, '\n'); + *cp++ = '\0'; + item = string_list_append(list, buf); + + buf = np + (*np == '\n'); + *np = '\0'; + cp = sq_dequote(cp); + if (!cp) + return error(_("unable to dequote value of '%s'"), + item->string); + item->util = xstrdup(cp); + } + return 0; +} + +/** + * Reads and parses the state directory's "author-script" file, and sets name, + * email and date accordingly. + * Returns 0 on success, -1 if the file could not be parsed. + * + * The author script is of the format: + * + * GIT_AUTHOR_NAME='$author_name' + * GIT_AUTHOR_EMAIL='$author_email' + * GIT_AUTHOR_DATE='$author_date' + * + * where $author_name, $author_email and $author_date are quoted. We are strict + * with our parsing, as the file was meant to be eval'd in the old + * git-am.sh/git-rebase--interactive.sh scripts, and thus if the file differs + * from what this function expects, it is better to bail out than to do + * something that the user does not expect. + */ +int read_author_script(const char *path, char **name, char **email, char **date, + int allow_missing) +{ + struct strbuf buf = STRBUF_INIT; + struct string_list kv = STRING_LIST_INIT_DUP; + int retval = -1; /* assume failure */ + int i, name_i = -2, email_i = -2, date_i = -2, err = 0; + + if (strbuf_read_file(&buf, path, 256) <= 0) { + strbuf_release(&buf); + if (errno == ENOENT && allow_missing) + return 0; + else + return error_errno(_("could not open '%s' for reading"), + path); + } + + if (parse_key_value_squoted(buf.buf, &kv)) + goto finish; + + for (i = 0; i < kv.nr; i++) { + if (!strcmp(kv.items[i].string, "GIT_AUTHOR_NAME")) { + if (name_i != -2) + name_i = error(_("'GIT_AUTHOR_NAME' already given")); + else + name_i = i; + } else if (!strcmp(kv.items[i].string, "GIT_AUTHOR_EMAIL")) { + if (email_i != -2) + email_i = error(_("'GIT_AUTHOR_EMAIL' already given")); + else + email_i = i; + } else if (!strcmp(kv.items[i].string, "GIT_AUTHOR_DATE")) { + if (date_i != -2) + date_i = error(_("'GIT_AUTHOR_DATE' already given")); + else + date_i = i; + } else { + err = error(_("unknown variable '%s'"), + kv.items[i].string); + } + } + if (name_i == -2) + error(_("missing 'GIT_AUTHOR_NAME'")); + if (email_i == -2) + error(_("missing 'GIT_AUTHOR_EMAIL'")); + if (date_i == -2) + error(_("missing 'GIT_AUTHOR_DATE'")); + if (date_i < 0 || email_i < 0 || date_i < 0 || err) + goto finish; + *name = kv.items[name_i].util; + *email = kv.items[email_i].util; + *date = kv.items[date_i].util; + retval = 0; +finish: + string_list_clear(&kv, !!retval); + strbuf_release(&buf); + return retval; +} /* * write_author_script() used to fail to terminate the last line with a "'" and diff --git a/sequencer.h b/sequencer.h index c986bc8251..60f15a4d9c 100644 --- a/sequencer.h +++ b/sequencer.h @@ -114,4 +114,7 @@ void commit_post_rewrite(const struct commit *current_head, #define SUMMARY_SHOW_AUTHOR_DATE (1 << 1) void print_commit_summary(const char *prefix, const struct object_id *oid, unsigned int flags); + +int read_author_script(const char *path, char **name, char **email, char **date, + int allow_missing); #endif -- cgit v1.2.3 From 4d010a757c40d6e6e478354991bd052ef30cb853 Mon Sep 17 00:00:00 2001 From: Phillip Wood Date: Wed, 31 Oct 2018 10:15:56 +0000 Subject: sequencer: use read_author_script() Use the new function added in the last commit to read the author script, updating read_env_script() and read_author_ident(). We now have a single code path that reads the author script for am and all flavors of rebase. This changes the behavior of read_env_script() as previously it would set any environment variables that were in the author-script file. Now it is an error if the file contains other variables or any of GIT_AUTHOR_NAME, GIT_AUTHOR_EMAIL and GIT_AUTHOR_DATE are missing. This is what am and the non interactive version of rebase have been doing for several years so hopefully it will not cause a problem for interactive rebase users. The advantage is that we are reusing existing code from am which uses sq_dequote() to properly dequote variables. This fixes potential problems with user edited scripts as read_env_script() which did not track quotes properly. This commit also removes the fallback code for checking for a broken author script after git is upgraded when a rebase is stopped. Now that the parsing uses sq_dequote() it will reliably return an error if the quoting is broken and the user will have to abort the rebase and restart. This isn't ideal but it's a corner case and the detection of the broken quoting could be confused by user edited author scripts. Signed-off-by: Phillip Wood Signed-off-by: Junio C Hamano --- sequencer.c | 97 +++++++++++++------------------------------------------------ 1 file changed, 21 insertions(+), 76 deletions(-) diff --git a/sequencer.c b/sequencer.c index bf84a4f8ea..ac8e506464 100644 --- a/sequencer.c +++ b/sequencer.c @@ -771,53 +771,24 @@ finish: } /* - * write_author_script() used to fail to terminate the last line with a "'" and - * also escaped "'" incorrectly as "'\\\\''" rather than "'\\''". We check for - * the terminating "'" on the last line to see how "'" has been escaped in case - * git was upgraded while rebase was stopped. - */ -static int quoting_is_broken(const char *s, size_t n) -{ - /* Skip any empty lines in case the file was hand edited */ - while (n > 0 && s[--n] == '\n') - ; /* empty */ - if (n > 0 && s[n] != '\'') - return 1; - - return 0; -} - -/* - * Read a list of environment variable assignments (such as the author-script - * file) into an environment block. Returns -1 on error, 0 otherwise. + * Read a GIT_AUTHOR_NAME, GIT_AUTHOR_EMAIL AND GIT_AUTHOR_DATE from a + * file with shell quoting into struct argv_array. Returns -1 on + * error, 0 otherwise. */ static int read_env_script(struct argv_array *env) { - struct strbuf script = STRBUF_INIT; - int i, count = 0, sq_bug; - const char *p2; - char *p; + char *name, *email, *date; - if (strbuf_read_file(&script, rebase_path_author_script(), 256) <= 0) + if (read_author_script(rebase_path_author_script(), + &name, &email, &date, 0)) return -1; - /* write_author_script() used to quote incorrectly */ - sq_bug = quoting_is_broken(script.buf, script.len); - for (p = script.buf; *p; p++) - if (sq_bug && skip_prefix(p, "'\\\\''", &p2)) - strbuf_splice(&script, p - script.buf, p2 - p, "'", 1); - else if (skip_prefix(p, "'\\''", &p2)) - strbuf_splice(&script, p - script.buf, p2 - p, "'", 1); - else if (*p == '\'') - strbuf_splice(&script, p-- - script.buf, 1, "", 0); - else if (*p == '\n') { - *p = '\0'; - count++; - } - for (i = 0, p = script.buf; i < count; i++) { - argv_array_push(env, p); - p += strlen(p) + 1; - } + argv_array_pushf(env, "GIT_AUTHOR_NAME=%s", name); + argv_array_pushf(env, "GIT_AUTHOR_EMAIL=%s", email); + argv_array_pushf(env, "GIT_AUTHOR_DATE=%s", date); + free(name); + free(email); + free(date); return 0; } @@ -837,54 +808,28 @@ static char *get_author(const char *message) /* Read author-script and return an ident line (author timestamp) */ static const char *read_author_ident(struct strbuf *buf) { - const char *keys[] = { - "GIT_AUTHOR_NAME=", "GIT_AUTHOR_EMAIL=", "GIT_AUTHOR_DATE=" - }; struct strbuf out = STRBUF_INIT; - char *in, *eol; - const char *val[3]; - int i = 0; + char *name, *email, *date; - if (strbuf_read_file(buf, rebase_path_author_script(), 256) <= 0) + if (read_author_script(rebase_path_author_script(), + &name, &email, &date, 0)) return NULL; - /* dequote values and construct ident line in-place */ - for (in = buf->buf; i < 3 && in - buf->buf < buf->len; i++) { - if (!skip_prefix(in, keys[i], (const char **)&in)) { - warning(_("could not parse '%s' (looking for '%s')"), - rebase_path_author_script(), keys[i]); - return NULL; - } - - eol = strchrnul(in, '\n'); - *eol = '\0'; - if (!sq_dequote(in)) { - warning(_("bad quoting on %s value in '%s'"), - keys[i], rebase_path_author_script()); - return NULL; - } - val[i] = in; - in = eol + 1; - } - - if (i < 3) { - warning(_("could not parse '%s' (looking for '%s')"), - rebase_path_author_script(), keys[i]); - return NULL; - } - /* validate date since fmt_ident() will die() on bad value */ - if (parse_date(val[2], &out)){ + if (parse_date(date, &out)){ warning(_("invalid date format '%s' in '%s'"), - val[2], rebase_path_author_script()); + date, rebase_path_author_script()); strbuf_release(&out); return NULL; } strbuf_reset(&out); - strbuf_addstr(&out, fmt_ident(val[0], val[1], val[2], 0)); + strbuf_addstr(&out, fmt_ident(name, email, date, 0)); strbuf_swap(buf, &out); strbuf_release(&out); + free(name); + free(email); + free(date); return buf->buf; } -- cgit v1.2.3