From 7bbf5a65c144ab91c4694275e3f280e4afe54881 Mon Sep 17 00:00:00 2001
From: Doug Coleman <doug.coleman@gmail.com>
Date: Wed, 17 Dec 2014 16:44:21 -0800
Subject: [PATCH] subrip-subtitles: Add parser for .srt files. Kind of ugly.

---
 extra/subrip-subtitles/authors.txt            |  1 +
 .../subrip-subtitles-tests.factor             | 60 +++++++++++++++++++
 .../subrip-subtitles/subrip-subtitles.factor  | 47 +++++++++++++++
 3 files changed, 108 insertions(+)
 create mode 100644 extra/subrip-subtitles/authors.txt
 create mode 100644 extra/subrip-subtitles/subrip-subtitles-tests.factor
 create mode 100644 extra/subrip-subtitles/subrip-subtitles.factor

diff --git a/extra/subrip-subtitles/authors.txt b/extra/subrip-subtitles/authors.txt
new file mode 100644
index 0000000000..7c1b2f2279
--- /dev/null
+++ b/extra/subrip-subtitles/authors.txt
@@ -0,0 +1 @@
+Doug Coleman
diff --git a/extra/subrip-subtitles/subrip-subtitles-tests.factor b/extra/subrip-subtitles/subrip-subtitles-tests.factor
new file mode 100644
index 0000000000..b90346f687
--- /dev/null
+++ b/extra/subrip-subtitles/subrip-subtitles-tests.factor
@@ -0,0 +1,60 @@
+! Copyright (C) 2014 Doug Coleman.
+! See http://factorcode.org/license.txt for BSD license.
+USING: calendar subrip-subtitles tools.test ;
+IN: subrip-subtitles.tests
+
+{
+    {
+        T{ srt-chunk
+            { id 1 }
+            { begin-time T{ duration { second 10.5 } } }
+            { end-time T{ duration { second 13.0 } } }
+            { text "Elephant's Dream" }
+        }
+        T{ srt-chunk
+            { id 2 }
+            { begin-time T{ duration { second 15.0 } } }
+            { end-time T{ duration { second 18.0 } } }
+            { text "At the left we can see..." }
+        }
+    }
+} [
+"""1
+00:00:10,500 --> 00:00:13,000
+Elephant's Dream
+
+2
+00:00:15,000 --> 00:00:18,000
+At the left we can see..."""
+    parse-srt-string
+] unit-test
+
+{
+    {
+        T{ srt-chunk
+            { id 1 }
+            { begin-time T{ duration { second 10.5 } } }
+            { end-time T{ duration { second 13.0 } } }
+            { rect { { 63 43 } { 223 58 } } }
+            { text "<i>Elephant's Dream</i>" }
+        }
+        T{ srt-chunk
+            { id 2 }
+            { begin-time T{ duration { second 15.0 } } }
+            { end-time T{ duration { second 18.0 } } }
+            { rect { { 53 438 } { 303 453 } } }
+            { text
+                "<font color=\"cyan\">At the left we can see...</font>"
+            }
+        }
+    }
+} [
+"""1
+00:00:10,500 --> 00:00:13,000  X1:63 X2:223 Y1:43 Y2:58
+<i>Elephant's Dream</i>
+
+2
+00:00:15,000 --> 00:00:18,000  X1:53 X2:303 Y1:438 Y2:453
+<font color="cyan">At the left we can see...</font>""" 
+    parse-srt-string
+] unit-test
diff --git a/extra/subrip-subtitles/subrip-subtitles.factor b/extra/subrip-subtitles/subrip-subtitles.factor
new file mode 100644
index 0000000000..e7d2cb8eb1
--- /dev/null
+++ b/extra/subrip-subtitles/subrip-subtitles.factor
@@ -0,0 +1,47 @@
+! Copyright (C) 2014 Doug Coleman.
+! See http://factorcode.org/license.txt for BSD license.
+USING: accessors arrays calendar calendar.format
+io.encodings.utf8 io.files io.streams.string kernel math
+math.parser sequences splitting ascii ;
+IN: subrip-subtitles
+
+! http://en.wikipedia.org/wiki/SubRip
+! .srt
+
+TUPLE: srt-chunk id begin-time end-time rect text ;
+
+: read-srt-timestamp ( -- duration )
+    instant
+    read-00 >>hour ":" expect
+    read-00 >>minute ":" expect
+    read-00 "," expect
+    read-000 1000 /f + >>second ;
+
+: parse-srt-timestamp ( string -- duration )
+    [ read-srt-timestamp ] with-string-reader ;
+
+: parse-srt-chunk ( seq -- srt-chunk )
+    [ ?first string>number ]
+    [
+        ?second "  " split1
+        [ "-->" split1 [ [ blank? ] trim parse-srt-timestamp ] bi@ ]
+        [
+            [ blank? ] trim " " split sift [
+                f
+            ] [
+                [ ":" split1 nip string>number ] map
+                first4 swapd [ 2array ] 2dip 2array 2array
+            ] if-empty
+        ] bi*
+    ] 
+    [ 2 tail "\n" join ] tri srt-chunk boa ;
+
+: parse-srt-lines ( seq -- seq' )
+    { "" } split harvest
+    [ parse-srt-chunk ] { } map-as ;
+
+: parse-srt-string ( seq -- seq' )
+    string-lines parse-srt-lines ;
+
+: parse-srt-file ( path -- seq )
+    utf8 file-lines parse-srt-lines ;