[PATCH v3 0/5] add --format=text0 to notmuch search

[PATCH v3 0/5] add --format=text0 to notmuch search

[Jani Nikula]

Hi all, v3 of id:cover.1355064714.git.jani@nikula.org

Changes since v2:
 * add new patch 1/5 to clarify sprinter documentation
 * fix the test patch 4/5 according to id:8738z6wguj.fsf@qmul.ac.uk and
   id:87y5gyvvv7.fsf@awakening.csail.mit.edu

Diff to v2 at the end of the cover letter.


BR,
Jani.


Jani Nikula (5):
  sprinter: clarify separator documentation
  sprinter: add text0 formatter for null character separated text
  cli: add --format=text0 to notmuch search
  test: notmuch search --format=text0
  man: document notmuch search --format=text0

 man/man1/notmuch-search.1 |   26 ++++++++++++++++----------
 notmuch-search.c          |   16 ++++++++++++++--
 sprinter-text.c           |   22 ++++++++++++++++++++++
 sprinter.h                |   15 +++++++++++----
 test/text                 |   33 +++++++++++++++++++++++++++++++++
 5 files changed, 96 insertions(+), 16 deletions(-)

-- 
1.7.10.4



diff --git a/sprinter.h b/sprinter.h
index f36b999..f859672 100644
--- a/sprinter.h
+++ b/sprinter.h
@@ -42,10 +42,11 @@ typedef struct sprinter {
      */
     void (*map_key) (struct sprinter *, const char *);
 
-    /* Insert a separator (usually extra whitespace) for improved
-     * readability without affecting the abstract syntax of the
-     * structure being printed.
-     * For JSON, this could simply be a line break.
+    /* Insert a separator (usually extra whitespace). For the text
+     * printers, this is a syntactic separator. For the structured
+     * printers, this is for improved readability without affecting
+     * the abstract syntax of the structure being printed. For JSON,
+     * this could simply be a line break.
      */
     void (*separator) (struct sprinter *);
 
diff --git a/test/text b/test/text
index e003a66..b5ccefc 100755
--- a/test/text
+++ b/test/text
@@ -55,30 +55,34 @@ test_expect_equal "$output" \
 add_email_corpus
 
 test_begin_subtest "Search message tags: text0"
-cat <<EOF > EXPECTED.$test_count
+cat <<EOF > EXPECTED
 attachment inbox signed unread
 EOF
-notmuch search --format=text0 --output=tags '*' | xargs -0 | notmuch_search_sanitize > OUTPUT.$test_count
-test_expect_equal_file EXPECTED.$test_count OUTPUT.$test_count
+notmuch search --format=text0 --output=tags '*' | xargs -0 | notmuch_search_sanitize > OUTPUT
+test_expect_equal_file EXPECTED OUTPUT
 
+# Use tr(1) to convert --output=text0 to --output=text for
+# comparison. Also translate newlines to spaces to fail with more
+# noise if they are present as delimiters instead of null
+# characters. This assumes there are no newlines in the data.
 test_begin_subtest "Compare text vs. text0 for threads"
-notmuch search --format=text --output=threads '*' | notmuch_search_sanitize > EXPECTED.$test_count
-notmuch search --format=text0 --output=threads '*' | xargs -0 -L1 | notmuch_search_sanitize > OUTPUT.$test_count
-test_expect_equal_file EXPECTED.$test_count OUTPUT.$test_count
+notmuch search --format=text --output=threads '*' | notmuch_search_sanitize > EXPECTED
+notmuch search --format=text0 --output=threads '*' | tr "\n\0" " \n" | notmuch_search_sanitize > OUTPUT
+test_expect_equal_file EXPECTED OUTPUT
 
 test_begin_subtest "Compare text vs. text0 for messages"
-notmuch search --format=text --output=messages '*' | notmuch_search_sanitize > EXPECTED.$test_count
-notmuch search --format=text0 --output=messages '*' | xargs -0 -L1 | notmuch_search_sanitize > OUTPUT.$test_count
-test_expect_equal_file EXPECTED.$test_count OUTPUT.$test_count
+notmuch search --format=text --output=messages '*' | notmuch_search_sanitize > EXPECTED
+notmuch search --format=text0 --output=messages '*' | tr "\n\0" " \n" | notmuch_search_sanitize > OUTPUT
+test_expect_equal_file EXPECTED OUTPUT
 
 test_begin_subtest "Compare text vs. text0 for files"
-notmuch search --format=text --output=files '*' | notmuch_search_sanitize > EXPECTED.$test_count
-notmuch search --format=text0 --output=files '*' | xargs -0 -L1 | notmuch_search_sanitize > OUTPUT.$test_count
-test_expect_equal_file EXPECTED.$test_count OUTPUT.$test_count
+notmuch search --format=text --output=files '*' | notmuch_search_sanitize > EXPECTED
+notmuch search --format=text0 --output=files '*' | tr "\n\0" " \n" | notmuch_search_sanitize > OUTPUT
+test_expect_equal_file EXPECTED OUTPUT
 
 test_begin_subtest "Compare text vs. text0 for tags"
-notmuch search --format=text --output=tags '*' | notmuch_search_sanitize > EXPECTED.$test_count
-notmuch search --format=text0 --output=tags '*' | xargs -0 -L1 | notmuch_search_sanitize > OUTPUT.$test_count
-test_expect_equal_file EXPECTED.$test_count OUTPUT.$test_count
+notmuch search --format=text --output=tags '*' | notmuch_search_sanitize > EXPECTED
+notmuch search --format=text0 --output=tags '*' | tr "\n\0" " \n" | notmuch_search_sanitize > OUTPUT
+test_expect_equal_file EXPECTED OUTPUT
 
 test_done

[PATCH v3 1/5] sprinter: clarify separator documentation

[Jani Nikula]

For text printers, the separator is a syntactic element.
---
 sprinter.h |    9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/sprinter.h b/sprinter.h
index 59776a9..f43a844 100644
--- a/sprinter.h
+++ b/sprinter.h
@@ -42,10 +42,11 @@ typedef struct sprinter {
      */
     void (*map_key) (struct sprinter *, const char *);
 
-    /* Insert a separator (usually extra whitespace) for improved
-     * readability without affecting the abstract syntax of the
-     * structure being printed.
-     * For JSON, this could simply be a line break.
+    /* Insert a separator (usually extra whitespace). For the text
+     * printers, this is a syntactic separator. For the structured
+     * printers, this is for improved readability without affecting
+     * the abstract syntax of the structure being printed. For JSON,
+     * this could simply be a line break.
      */
     void (*separator) (struct sprinter *);
 
-- 
1.7.10.4

[PATCH v3 2/5] sprinter: add text0 formatter for null character separated text

[Jani Nikula]

Same as the text formatter, but with each field separated by a null
character rather than a newline character.
---
 sprinter-text.c |   22 ++++++++++++++++++++++
 sprinter.h      |    6 ++++++
 2 files changed, 28 insertions(+)

diff --git a/sprinter-text.c b/sprinter-text.c
index 10343be..7779488 100644
--- a/sprinter-text.c
+++ b/sprinter-text.c
@@ -68,6 +68,14 @@ text_separator (struct sprinter *sp)
 }
 
 static void
+text0_separator (struct sprinter *sp)
+{
+    struct sprinter_text *sptxt = (struct sprinter_text *) sp;
+
+    fputc ('\0', sptxt->stream);
+}
+
+static void
 text_set_prefix (struct sprinter *sp, const char *prefix)
 {
     struct sprinter_text *sptxt = (struct sprinter_text *) sp;
@@ -133,3 +141,17 @@ sprinter_text_create (const void *ctx, FILE *stream)
     res->stream = stream;
     return &res->vtable;
 }
+
+struct sprinter *
+sprinter_text0_create (const void *ctx, FILE *stream)
+{
+    struct sprinter *sp;
+
+    sp = sprinter_text_create (ctx, stream);
+    if (! sp)
+	return NULL;
+
+    sp->separator = text0_separator;
+
+    return sp;
+}
diff --git a/sprinter.h b/sprinter.h
index f43a844..f859672 100644
--- a/sprinter.h
+++ b/sprinter.h
@@ -67,6 +67,12 @@ typedef struct sprinter {
 struct sprinter *
 sprinter_text_create (const void *ctx, FILE *stream);
 
+/* Create a new unstructured printer that emits the text format for
+ * "notmuch search", with each field separated by a null character
+ * instead of the newline character. */
+struct sprinter *
+sprinter_text0_create (const void *ctx, FILE *stream);
+
 /* Create a new structure printer that emits JSON. */
 struct sprinter *
 sprinter_json_create (const void *ctx, FILE *stream);
-- 
1.7.10.4

[PATCH v3 3/5] cli: add --format=text0 to notmuch search

[Jani Nikula]

Add new format text0, which is otherwise the same as text, but use the
null character as separator instead of the newline character. This is
similar to find(1) -print0 option, and works together with the
xargs(1) -0 option.
---
 notmuch-search.c |   16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/notmuch-search.c b/notmuch-search.c
index 6218622..627962b 100644
--- a/notmuch-search.c
+++ b/notmuch-search.c
@@ -305,8 +305,12 @@ notmuch_search_command (void *ctx, int argc, char *argv[])
     int exclude = EXCLUDE_TRUE;
     unsigned int i;
 
-    enum { NOTMUCH_FORMAT_JSON, NOTMUCH_FORMAT_TEXT, NOTMUCH_FORMAT_SEXP }
-	format_sel = NOTMUCH_FORMAT_TEXT;
+    enum {
+	NOTMUCH_FORMAT_JSON,
+	NOTMUCH_FORMAT_TEXT,
+	NOTMUCH_FORMAT_TEXT0,
+	NOTMUCH_FORMAT_SEXP
+    } format_sel = NOTMUCH_FORMAT_TEXT;
 
     notmuch_opt_desc_t options[] = {
 	{ NOTMUCH_OPT_KEYWORD, &sort, "sort", 's',
@@ -317,6 +321,7 @@ notmuch_search_command (void *ctx, int argc, char *argv[])
 	  (notmuch_keyword_t []){ { "json", NOTMUCH_FORMAT_JSON },
 				  { "sexp", NOTMUCH_FORMAT_SEXP },
 				  { "text", NOTMUCH_FORMAT_TEXT },
+				  { "text0", NOTMUCH_FORMAT_TEXT0 },
 				  { 0, 0 } } },
 	{ NOTMUCH_OPT_KEYWORD, &output, "output", 'o',
 	  (notmuch_keyword_t []){ { "summary", OUTPUT_SUMMARY },
@@ -345,6 +350,13 @@ notmuch_search_command (void *ctx, int argc, char *argv[])
     case NOTMUCH_FORMAT_TEXT:
 	format = sprinter_text_create (ctx, stdout);
 	break;
+    case NOTMUCH_FORMAT_TEXT0:
+	if (output == OUTPUT_SUMMARY) {
+	    fprintf (stderr, "Error: --format=text0 is not compatible with --output=summary.\n");
+	    return 1;
+	}
+	format = sprinter_text0_create (ctx, stdout);
+	break;
     case NOTMUCH_FORMAT_JSON:
 	format = sprinter_json_create (ctx, stdout);
 	break;
-- 
1.7.10.4

[PATCH v3 4/5] test: notmuch search --format=text0

[Jani Nikula]

---
 test/text |   33 +++++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/test/text b/test/text
index 428c89b..b5ccefc 100755
--- a/test/text
+++ b/test/text
@@ -52,4 +52,37 @@ output=$(notmuch search --format=text "tëxt-search-méssage" | notmuch_search_s
 test_expect_equal "$output" \
 "thread:XXX   2000-01-01 [1/1] Notmuch Test Suite; text-search-utf8-body-sübjéct (inbox unread)"
 
+add_email_corpus
+
+test_begin_subtest "Search message tags: text0"
+cat <<EOF > EXPECTED
+attachment inbox signed unread
+EOF
+notmuch search --format=text0 --output=tags '*' | xargs -0 | notmuch_search_sanitize > OUTPUT
+test_expect_equal_file EXPECTED OUTPUT
+
+# Use tr(1) to convert --output=text0 to --output=text for
+# comparison. Also translate newlines to spaces to fail with more
+# noise if they are present as delimiters instead of null
+# characters. This assumes there are no newlines in the data.
+test_begin_subtest "Compare text vs. text0 for threads"
+notmuch search --format=text --output=threads '*' | notmuch_search_sanitize > EXPECTED
+notmuch search --format=text0 --output=threads '*' | tr "\n\0" " \n" | notmuch_search_sanitize > OUTPUT
+test_expect_equal_file EXPECTED OUTPUT
+
+test_begin_subtest "Compare text vs. text0 for messages"
+notmuch search --format=text --output=messages '*' | notmuch_search_sanitize > EXPECTED
+notmuch search --format=text0 --output=messages '*' | tr "\n\0" " \n" | notmuch_search_sanitize > OUTPUT
+test_expect_equal_file EXPECTED OUTPUT
+
+test_begin_subtest "Compare text vs. text0 for files"
+notmuch search --format=text --output=files '*' | notmuch_search_sanitize > EXPECTED
+notmuch search --format=text0 --output=files '*' | tr "\n\0" " \n" | notmuch_search_sanitize > OUTPUT
+test_expect_equal_file EXPECTED OUTPUT
+
+test_begin_subtest "Compare text vs. text0 for tags"
+notmuch search --format=text --output=tags '*' | notmuch_search_sanitize > EXPECTED
+notmuch search --format=text0 --output=tags '*' | tr "\n\0" " \n" | notmuch_search_sanitize > OUTPUT
+test_expect_equal_file EXPECTED OUTPUT
+
 test_done
-- 
1.7.10.4

[PATCH v3 5/5] man: document notmuch search --format=text0

[Jani Nikula]

---
 man/man1/notmuch-search.1 |   26 ++++++++++++++++----------
 1 file changed, 16 insertions(+), 10 deletions(-)

diff --git a/man/man1/notmuch-search.1 b/man/man1/notmuch-search.1
index 0aff348..22bcd0a 100644
--- a/man/man1/notmuch-search.1
+++ b/man/man1/notmuch-search.1
@@ -25,9 +25,11 @@ Supported options for
 include
 .RS 4
 .TP 4
-.BR \-\-format= ( json | sexp | text )
+.BR \-\-format= ( json | sexp | text | text0 )
 
-Presents the results in either JSON, S-Expressions or plain-text (default).
+Presents the results in either JSON, S-Expressions, newline character
+separated plain-text (default), or null character separated plain-text
+(compatible with \fBxargs\fR(1) -0 option where available).
 .RE
 
 .RS 4
@@ -48,32 +50,36 @@ the authors of the thread and the subject.
 .B threads
 
 Output the thread IDs of all threads with any message matching the
-search terms, either one per line (\-\-format=text) or as a JSON array
-(\-\-format=json) or an S-Expression list (\-\-format=sexp).
+search terms, either one per line (\-\-format=text), separated by null
+characters (\-\-format=text0), as a JSON array (\-\-format=json), or
+an S-Expression list (\-\-format=sexp).
 .RE
 .RS 4
 .TP 4
 .B messages
 
 Output the message IDs of all messages matching the search terms,
-either one per line (\-\-format=text) or as a JSON array
-(\-\-format=json) or as an S-Expression list (\-\-format=sexp).
+either one per line (\-\-format=text), separated by null characters
+(\-\-format=text0), as a JSON array (\-\-format=json), or as an
+S-Expression list (\-\-format=sexp).
 .RE
 .RS 4
 .TP 4
 .B files
 
 Output the filenames of all messages matching the search terms, either
-one per line (\-\-format=text) or as a JSON array (\-\-format=json) or
-as an S-Expression list (\-\-format=sexp).
+one per line (\-\-format=text), separated by null characters
+(\-\-format=text0), as a JSON array (\-\-format=json), or as an
+S-Expression list (\-\-format=sexp).
 .RE
 .RS 4
 .TP 4
 .B tags
 
 Output all tags that appear on any message matching the search terms,
-either one per line (\-\-format=text) or as a JSON array (\-\-format=json)
-or as an S-Expression list (\-\-format=sexp).
+either one per line (\-\-format=text), separated by null characters
+(\-\-format=text0), as a JSON array (\-\-format=json), or as an
+S-Expression list (\-\-format=sexp).
 .RE
 .RE
 
-- 
1.7.10.4

Re: [PATCH v3 0/5] add --format=text0 to notmuch search

[Austin Clements]

On Sun, 16 Dec 2012, Jani Nikula <jani@nikula.org> wrote:
> Hi all, v3 of id:cover.1355064714.git.jani@nikula.org
>
> Changes since v2:
>  * add new patch 1/5 to clarify sprinter documentation
>  * fix the test patch 4/5 according to id:8738z6wguj.fsf@qmul.ac.uk and
>    id:87y5gyvvv7.fsf@awakening.csail.mit.edu
>
> Diff to v2 at the end of the cover letter.
>
>
> BR,
> Jani.

LGTM.

Re: [PATCH v3 0/5] add --format=text0 to notmuch search

[Mark Walters]

On Sun, 16 Dec 2012, Jani Nikula <jani@nikula.org> wrote:
> Hi all, v3 of id:cover.1355064714.git.jani@nikula.org
>
> Changes since v2:
>  * add new patch 1/5 to clarify sprinter documentation
>  * fix the test patch 4/5 according to id:8738z6wguj.fsf@qmul.ac.uk and
>    id:87y5gyvvv7.fsf@awakening.csail.mit.edu
>
> Diff to v2 at the end of the cover letter.

LGTM +1

Best wishes

Mark



>
>
> BR,
> Jani.
>
>
> Jani Nikula (5):
>   sprinter: clarify separator documentation
>   sprinter: add text0 formatter for null character separated text
>   cli: add --format=text0 to notmuch search
>   test: notmuch search --format=text0
>   man: document notmuch search --format=text0
>
>  man/man1/notmuch-search.1 |   26 ++++++++++++++++----------
>  notmuch-search.c          |   16 ++++++++++++++--
>  sprinter-text.c           |   22 ++++++++++++++++++++++
>  sprinter.h                |   15 +++++++++++----
>  test/text                 |   33 +++++++++++++++++++++++++++++++++
>  5 files changed, 96 insertions(+), 16 deletions(-)
>
> -- 
> 1.7.10.4
>
>
>
> diff --git a/sprinter.h b/sprinter.h
> index f36b999..f859672 100644
> --- a/sprinter.h
> +++ b/sprinter.h
> @@ -42,10 +42,11 @@ typedef struct sprinter {
>       */
>      void (*map_key) (struct sprinter *, const char *);
>  
> -    /* Insert a separator (usually extra whitespace) for improved
> -     * readability without affecting the abstract syntax of the
> -     * structure being printed.
> -     * For JSON, this could simply be a line break.
> +    /* Insert a separator (usually extra whitespace). For the text
> +     * printers, this is a syntactic separator. For the structured
> +     * printers, this is for improved readability without affecting
> +     * the abstract syntax of the structure being printed. For JSON,
> +     * this could simply be a line break.
>       */
>      void (*separator) (struct sprinter *);
>  
> diff --git a/test/text b/test/text
> index e003a66..b5ccefc 100755
> --- a/test/text
> +++ b/test/text
> @@ -55,30 +55,34 @@ test_expect_equal "$output" \
>  add_email_corpus
>  
>  test_begin_subtest "Search message tags: text0"
> -cat <<EOF > EXPECTED.$test_count
> +cat <<EOF > EXPECTED
>  attachment inbox signed unread
>  EOF
> -notmuch search --format=text0 --output=tags '*' | xargs -0 | notmuch_search_sanitize > OUTPUT.$test_count
> -test_expect_equal_file EXPECTED.$test_count OUTPUT.$test_count
> +notmuch search --format=text0 --output=tags '*' | xargs -0 | notmuch_search_sanitize > OUTPUT
> +test_expect_equal_file EXPECTED OUTPUT
>  
> +# Use tr(1) to convert --output=text0 to --output=text for
> +# comparison. Also translate newlines to spaces to fail with more
> +# noise if they are present as delimiters instead of null
> +# characters. This assumes there are no newlines in the data.
>  test_begin_subtest "Compare text vs. text0 for threads"
> -notmuch search --format=text --output=threads '*' | notmuch_search_sanitize > EXPECTED.$test_count
> -notmuch search --format=text0 --output=threads '*' | xargs -0 -L1 | notmuch_search_sanitize > OUTPUT.$test_count
> -test_expect_equal_file EXPECTED.$test_count OUTPUT.$test_count
> +notmuch search --format=text --output=threads '*' | notmuch_search_sanitize > EXPECTED
> +notmuch search --format=text0 --output=threads '*' | tr "\n\0" " \n" | notmuch_search_sanitize > OUTPUT
> +test_expect_equal_file EXPECTED OUTPUT
>  
>  test_begin_subtest "Compare text vs. text0 for messages"
> -notmuch search --format=text --output=messages '*' | notmuch_search_sanitize > EXPECTED.$test_count
> -notmuch search --format=text0 --output=messages '*' | xargs -0 -L1 | notmuch_search_sanitize > OUTPUT.$test_count
> -test_expect_equal_file EXPECTED.$test_count OUTPUT.$test_count
> +notmuch search --format=text --output=messages '*' | notmuch_search_sanitize > EXPECTED
> +notmuch search --format=text0 --output=messages '*' | tr "\n\0" " \n" | notmuch_search_sanitize > OUTPUT
> +test_expect_equal_file EXPECTED OUTPUT
>  
>  test_begin_subtest "Compare text vs. text0 for files"
> -notmuch search --format=text --output=files '*' | notmuch_search_sanitize > EXPECTED.$test_count
> -notmuch search --format=text0 --output=files '*' | xargs -0 -L1 | notmuch_search_sanitize > OUTPUT.$test_count
> -test_expect_equal_file EXPECTED.$test_count OUTPUT.$test_count
> +notmuch search --format=text --output=files '*' | notmuch_search_sanitize > EXPECTED
> +notmuch search --format=text0 --output=files '*' | tr "\n\0" " \n" | notmuch_search_sanitize > OUTPUT
> +test_expect_equal_file EXPECTED OUTPUT
>  
>  test_begin_subtest "Compare text vs. text0 for tags"
> -notmuch search --format=text --output=tags '*' | notmuch_search_sanitize > EXPECTED.$test_count
> -notmuch search --format=text0 --output=tags '*' | xargs -0 -L1 | notmuch_search_sanitize > OUTPUT.$test_count
> -test_expect_equal_file EXPECTED.$test_count OUTPUT.$test_count
> +notmuch search --format=text --output=tags '*' | notmuch_search_sanitize > EXPECTED
> +notmuch search --format=text0 --output=tags '*' | tr "\n\0" " \n" | notmuch_search_sanitize > OUTPUT
> +test_expect_equal_file EXPECTED OUTPUT
>  
>  test_done