[tracker-miners/sam/plain-text: 35/36] tracker-extract: Only index text/plain MIME types, never index source code



commit 606d9a135cd1a893ad806aa444bf1acc48fcf2a7
Author: Sam Thursfield <sam afuera me uk>
Date:   Thu Jun 18 00:24:42 2020 +0200

    tracker-extract: Only index text/plain MIME types, never index source code
    
    Tracker isn't and never will be a sourcecode indexer. Source
    code is often huge, and it requires some understanding and
    tokenization of the contents in order to effectively create
    an index. Tracker indexes text documents by copying the
    first 1MB of data from each file into an SQLite database.

 src/tracker-extract/15-source-code.rule                    | 6 ------
 src/tracker-extract/{90-text-generic.rule => 15-text.rule} | 2 +-
 src/tracker-extract/meson.build                            | 2 +-
 3 files changed, 2 insertions(+), 8 deletions(-)
---
diff --git a/src/tracker-extract/90-text-generic.rule b/src/tracker-extract/15-text.rule
similarity index 79%
rename from src/tracker-extract/90-text-generic.rule
rename to src/tracker-extract/15-text.rule
index 661bc5061..9439262d4 100644
--- a/src/tracker-extract/90-text-generic.rule
+++ b/src/tracker-extract/15-text.rule
@@ -1,6 +1,6 @@
 [ExtractorRule]
 ModulePath=libextract-text.so
-MimeTypes=text/*
+MimeTypes=text/plain;text/markdown
 FallbackRdfTypes=nfo:Document;nfo:PlainTextDocument;
 Graph=tracker:Documents
 Hash=@hash@
diff --git a/src/tracker-extract/meson.build b/src/tracker-extract/meson.build
index 18cbeaaf9..c6a5c6127 100644
--- a/src/tracker-extract/meson.build
+++ b/src/tracker-extract/meson.build
@@ -90,7 +90,7 @@ if get_option('ps')
 endif
 
 if get_option('text')
-  modules += [['extract-text', 'tracker-extract-text.c', ['15-source-code.rule', '90-text-generic.rule'], 
[]]]
+  modules += [['extract-text', 'tracker-extract-text.c', ['15-text.rule'], []]]
 endif
 
 if libtiff.found()


[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]