From b75a0f9bb80733ec8e236ddd7d5ff4aee32acee8 Mon Sep 17 00:00:00 2001 From: Will Thompson Date: Fri, 11 Mar 2016 12:10:32 +0000 Subject: [PATCH 1/2] srt: neater docstrings, some cleanup --- ox/srt.py | 39 +++++++++++++++++++++++++-------------- 1 file changed, 25 insertions(+), 14 deletions(-) diff --git a/ox/srt.py b/ox/srt.py index ee5a982..1b3f8b3 100644 --- a/ox/srt.py +++ b/ox/srt.py @@ -51,11 +51,12 @@ def _detect_encoding(fp): def load(filename, offset=0): - ''' - filename path to an srt file - offset in seconds shift all in/out points by offset + '''Parses an srt file - returns list with objects that have in,out,value and id + filename: path to an srt file + offset (float, seconds): shift all in/out points by offset + + Returns list with dicts that have in, out, value and id ''' srt = [] @@ -87,20 +88,30 @@ def load(filename, offset=0): i += 1 return srt + +def _srt_timecode(t): + return ox.format_duration(t * 1000, years=False).replace('.', ',') + + def encode(data): - ''' - encodes list of objects with in,out,value into srt - result is utf-8 encoded bytestring - ''' + """Encodes subtitles into SRT format + + data: list of dicts with 'in', 'out': float and 'value': unicode + + Returns: a UTF-8-encoded bytestring + + >>> encode([{'in': 1.25, 'out': 60 * 60 + 1, 'value': u'touch\\u00E9'}]) + '\\xef\\xbb\\xbf1\\r\\n00:00:01,250 --> 01:00:01,000\\r\\ntouch\\xc3\\xa9\\r\\n\\r\\n' + """ + srt = u'' - i = 1 - for s in data: + + for i, s in enumerate(data, 1): srt += '%d\r\n%s --> %s\r\n%s\r\n\r\n' % ( i, - ox.format_duration(s['in']*1000, years=False).replace('.', ','), - ox.format_duration(s['out']*1000, years=False).replace('.', ','), + _srt_timecode(s['in']), + _srt_timecode(s['out']), s['value'].replace('\n', '\r\n').strip() ) - i += 1 + return codecs.BOM_UTF8 + srt.encode('utf-8') - -- 2.5.0