lib: index attachments with mime types matching index.as_text

Instead of skipping indexing all attachments, we check of a (user
configured) mime type that is indexable as text.

doc/man1/notmuch-config.rst

@@ -122,6 +122,16 @@ paths are presumed relative to `$HOME` for items in section
 
     Default tag prefix (filter) for :any:`notmuch-git`.
 
+.. nmconfig:: index.as_text
+
+   List of regular expressions (without delimiters) for MIME types to
+   be indexed as text. Currently this applies only to attachments.  By
+   default the regex matches anywhere in the content type; if they
+   user wants an anchored match, they should include anchors in their
+   regexes.
+
+   History: This configuration value was introduced in notmuch 0.38.
+
 .. nmconfig:: index.decrypt
 
     Policy for decrypting encrypted messages during indexing.  Must be

lib/database.cc

@@ -1573,3 +1573,15 @@ notmuch_database_status_string (const notmuch_database_t *notmuch)
 {
     return notmuch->status_string;
 }
+
+bool
+_notmuch_database_indexable_as_text (notmuch_database_t *notmuch, const char *mime_string)
+{
+    for (size_t i = 0; i < notmuch->index_as_text_length; i++) {
+	if (regexec (&notmuch->index_as_text[i], mime_string, 0, NULL, 0) == 0) {
+	    return true;
+	}
+    }
+
+    return false;
+}

lib/index.cc

@@ -380,6 +380,23 @@ _index_pkcs7_part (notmuch_message_t *message,
 		   GMimeObject *part,
 		   _notmuch_message_crypto_t *msg_crypto);
 
+static bool
+_indexable_as_text (notmuch_message_t *message, GMimeObject *part)
+{
+    GMimeContentType *content_type = g_mime_object_get_content_type (part);
+    notmuch_database_t *notmuch = notmuch_message_get_database (message);
+
+    if (content_type) {
+	char *mime_string = g_mime_content_type_get_mime_type (content_type);
+	if (mime_string) {
+	    bool ret = _notmuch_database_indexable_as_text (notmuch, mime_string);
+	    g_free (mime_string);
+	    return ret;
+	}
+    }
+    return false;
+}
+
 /* Callback to generate terms for each mime part of a message. */
 static void
 _index_mime_part (notmuch_message_t *message,
@@ -497,10 +514,12 @@ _index_mime_part (notmuch_message_t *message,
 	_notmuch_message_add_term (message, "tag", "attachment");
 	_notmuch_message_gen_terms (message, "attachment", filename);
 
+	if (! _indexable_as_text (message, part)) {
 	    /* XXX: Would be nice to call out to something here to parse
 	     * the attachment into text and then index that. */
 	    goto DONE;
 	}
+    }
 
     byte_array = g_byte_array_new ();
 

lib/notmuch-private.h

@@ -259,6 +259,10 @@ _notmuch_database_filename_to_direntry (void *ctx,
 					notmuch_find_flags_t flags,
 					char **direntry);
 
+bool
+_notmuch_database_indexable_as_text (notmuch_database_t *notmuch,
+				     const char *mime_string);
+
 /* directory.cc */
 
 notmuch_directory_t *

test/T050-new.sh

@@ -470,12 +470,4 @@ Date: Fri, 17 Jun 2016 22:14:41 -0400
 EOF
 test_expect_equal_file EXPECTED OUTPUT
 
-add_email_corpus indexing
-
-test_begin_subtest "index text/* attachments"
-test_subtest_known_broken
-notmuch search id:20200930101213.2m2pt3jrspvcrxfx@localhost.localdomain > EXPECTED
-notmuch search id:20200930101213.2m2pt3jrspvcrxfx@localhost.localdomain and ersatz > OUTPUT
-test_expect_equal_file_nonempty EXPECTED OUTPUT
-
 test_done

test/T760-as-text.sh

@@ -0,0 +1,77 @@
+#!/usr/bin/env bash
+test_description='index attachments as text'
+. $(dirname "$0")/test-lib.sh || exit 1
+
+add_email_corpus indexing
+test_begin_subtest "empty as_text; skip text/x-diff"
+messages=$(notmuch count id:20200930101213.2m2pt3jrspvcrxfx@localhost.localdomain)
+count=$(notmuch count id:20200930101213.2m2pt3jrspvcrxfx@localhost.localdomain and ersatz)
+test_expect_equal "$messages,$count" "1,0"
+
+notmuch config set index.as_text "^text/"
+add_email_corpus indexing
+
+test_begin_subtest "as_index is text/; find text/x-diff"
+notmuch search id:20200930101213.2m2pt3jrspvcrxfx@localhost.localdomain > EXPECTED
+notmuch search id:20200930101213.2m2pt3jrspvcrxfx@localhost.localdomain and ersatz > OUTPUT
+test_expect_equal_file_nonempty EXPECTED OUTPUT
+
+test_begin_subtest "reindex with empty as_text, skips text/x-diff"
+notmuch config set index.as_text
+notmuch reindex '*'
+messages=$(notmuch count id:20200930101213.2m2pt3jrspvcrxfx@localhost.localdomain)
+count=$(notmuch count id:20200930101213.2m2pt3jrspvcrxfx@localhost.localdomain and ersatz)
+test_expect_equal "$messages,$count" "1,0"
+
+test_begin_subtest "reindex with empty as_text; skips application/pdf"
+notmuch config set index.as_text
+notmuch reindex '*'
+gmessages=$(notmuch count id:871qo9p4tf.fsf@tethera.net)
+count=$(notmuch count id:871qo9p4tf.fsf@tethera.net and body:not-really-PDF)
+test_expect_equal "$messages,$count" "1,0"
+
+test_begin_subtest "reindex with as_text as text/; finds text/x-diff"
+notmuch config set index.as_text "^text/"
+notmuch reindex '*'
+notmuch search id:20200930101213.2m2pt3jrspvcrxfx@localhost.localdomain > EXPECTED
+notmuch search id:20200930101213.2m2pt3jrspvcrxfx@localhost.localdomain and ersatz > OUTPUT
+test_expect_equal_file_nonempty EXPECTED OUTPUT
+
+test_begin_subtest "reindex with as_text as text/; skips application/pdf"
+notmuch config set index.as_text "^text/"
+notmuch config set index.as_text
+notmuch reindex '*'
+messages=$(notmuch count id:871qo9p4tf.fsf@tethera.net)
+count=$(notmuch count id:871qo9p4tf.fsf@tethera.net and body:not-really-PDF)
+test_expect_equal "$messages,$count" "1,0"
+
+test_begin_subtest "as_text has multiple regexes"
+notmuch config set index.as_text "blahblah;^text/"
+notmuch reindex '*'
+notmuch search id:20200930101213.2m2pt3jrspvcrxfx@localhost.localdomain > EXPECTED
+notmuch search id:20200930101213.2m2pt3jrspvcrxfx@localhost.localdomain and ersatz > OUTPUT
+test_expect_equal_file_nonempty EXPECTED OUTPUT
+
+test_begin_subtest "as_text is non-anchored regex"
+notmuch config set index.as_text "e.t/"
+notmuch reindex '*'
+notmuch search id:20200930101213.2m2pt3jrspvcrxfx@localhost.localdomain > EXPECTED
+notmuch search id:20200930101213.2m2pt3jrspvcrxfx@localhost.localdomain and ersatz > OUTPUT
+test_expect_equal_file_nonempty EXPECTED OUTPUT
+
+test_begin_subtest "as_text is 'application/pdf'"
+notmuch config set index.as_text "^application/pdf$"
+notmuch reindex '*'
+notmuch search id:871qo9p4tf.fsf@tethera.net > EXPECTED
+notmuch search id:871qo9p4tf.fsf@tethera.net and '"not really PDF"' > OUTPUT
+test_expect_equal_file_nonempty EXPECTED OUTPUT
+
+test_begin_subtest "as_text is bad regex"
+notmuch config set index.as_text '['
+notmuch reindex '*' >& OUTPUT
+cat<<EOF > EXPECTED
+Error in index.as_text: Invalid regular expression: [
+EOF
+test_expect_equal_file EXPECTED OUTPUT
+
+test_done

test/corpora/indexing/fake-pdf:2,S

@@ -0,0 +1,11 @@
+From: David Bremner <david@tethera.net>
+To: example@example.com
+Subject: attachment content type
+Date: Thu, 05 Jan 2023 08:02:36 -0400
+Message-ID: <871qo9p4tf.fsf@tethera.net>
+MIME-Version: 1.0
+Content-Type: application/pdf
+Content-Disposition: attachment; filename=fake.pdf
+Content-Transfer-Encoding: base64
+
+dGhpcyBpcyBub3QgcmVhbGx5IFBERgo=