def test_sytax_warning(self):
with warnings.catch_warnings():
warnings.resetwarnings()
warnings.simplefilter("error", SyntaxWarning)
self.assertRaises(SyntaxWarning,list,usfm.parser(['\\id TEST\\mt \\whoops']))
self.assertRaises(SyntaxError, list,usfm.parser(['\\id TEST\\mt \\whoops'], error_level=sfm.level.Marker))
self.assertRaises(SyntaxWarning,list,usfm.parser(['\\id TEST\\mt \\zwhoops']))
self.assertRaises(SyntaxWarning,list,usfm.parser(['\\id TEST\\mt \\zwhoops'], error_level=sfm.level.Marker))
def test_footnote_content(self):
def ft(src, doc):
return (r'\id TEST\mt ' + src,
[elem('id', text('TEST'), elem('mt', doc))])
tests = [
ft(r'\f - bare text\f*', elem(('f', '-'), text('bare text'))),
ft(r'\f - \ft bare text\ft*\f*', elem(('f', '-'),
text('bare text'))),
ft(
r'\f + \fk Issac:\ft In Hebrew means "laughter"\f*',
elem(('f', '+'), elem('fk', text('Issac:')),
text('In Hebrew means "laughter"'))),
ft(
r'\f + \fk Issac:\fk*In Hebrew means "laughter"\f*',
elem(('f', '+'), elem('fk', text('Issac:')),
text('In Hebrew means "laughter"'))),
ft(
r'\f + \fr 1.14 \fq religious festivals;\ft or \fq seasons.\f*',
elem(('f', '+'), elem('fr', text('1.14 ')),
elem('fq', text('religious festivals;')), text('or '),
elem('fq', text('seasons.')))),
ft(
r'\f + \fr 1.14 \fr*\fq religious festivals;\fq*or \fq seasons.\fq*\f*',
elem(('f', '+'), elem('fr', text('1.14 ')),
elem('fq', text('religious festivals;')), text('or '),
elem('fq', text('seasons.'))))
]
for r in [(list(usfm.parser([s], error_level=usfm.level.Note)), r)
for s, r in tests]:
self.assertEqual(*r)
def test_inline_markers(self):
tests = [(r'\test', [elem('test')]),
(r'\test text', [elem('test'), text(' text')]),
(r'\id JHN\ior text\ior*', [elem('id',text('JHN'), elem('ior',text('text')))]),
(r'\id MAT\mt Text \f + \fk deep\fk*\f*more text.',[elem('id', text('MAT'), elem('mt', text('Text '), elem(('f','+'), elem('fk',text('deep'))), text('more text.')))])]
for r in [(list(usfm.parser([s], private=False)),r) for s,r in tests]:
self.assertEqual(*r)
def test_parameters(self):
tests = [(r'\id TEST' r'\c 1', [elem('id', text('TEST'), elem(('c','1')))]),
(r'\id TEST' r'\c 2 \s text', [elem('id', text('TEST'), elem(('c','2'), elem('s','text')))]),
(r'\id TEST\c 0\p' r'\v 1', [elem('id', text('TEST'), elem(('c','0'), elem('p', elem(('v','1')))))]),
(r'\id TEST\c 0\p' r'\v 1-3', [elem('id', text('TEST'), elem(('c','0'), elem('p', elem(('v','1-3')))))]),
(r'\id TEST\c 0\p' r'\v 2 text', [elem('id', text('TEST'), elem(('c','0'), elem('p', elem(('v','2')), text(' text'))))]),
(r'\id TEST' r'\c 2 \p \v 3 text\v 4 verse', [elem('id', text('TEST'), elem(('c','2'), elem('p', elem(('v','3')), text(' text'), elem(('v','4')), text(' verse'))))]),]
for r in [(list(usfm.parser([s], private=False)),r) for s,r in tests]:
self.assertEqual(*r)
def test_footnote_content(self):
def ft(src,doc): return (r'\id TEST\mt '+src, [elem('id', text('TEST'), elem('mt', doc))])
tests = [ft(r'\f - bare text\f*', elem(('f','-'), text('bare text'))),
ft(r'\f - \ft bare text\ft*\f*', elem(('f','-'), text('bare text'))),
ft(r'\f + \fk Issac:\ft In Hebrew means "laughter"\f*', elem(('f','+'), elem('fk',text('Issac:')), text('In Hebrew means "laughter"'))),
ft(r'\f + \fk Issac:\fk*In Hebrew means "laughter"\f*', elem(('f','+'), elem('fk',text('Issac:')), text('In Hebrew means "laughter"'))),
ft(r'\f + \fr 1.14 \fq religious festivals;\ft or \fq seasons.\f*', elem(('f','+'), elem('fr',text('1.14 ')), elem('fq',text('religious festivals;')), text('or '), elem('fq',text('seasons.')))),
ft(r'\f + \fr 1.14 \fr*\fq religious festivals;\fq*or \fq seasons.\fq*\f*', elem(('f','+'), elem('fr',text('1.14 ')), elem('fq',text('religious festivals;')), text('or '), elem('fq',text('seasons.'))))]
for r in [(list(usfm.parser([s], private=False)),r) for s,r in tests]:
self.assertEqual(*r)
def test_sytax_error(self):
# Chapter number parsing
self.assertRaises(SyntaxError,list,usfm.parser(['\\id TEST\\c\\p \\v 1 text']))
self.assertRaises(SyntaxError,list,usfm.parser(['\\id TEST\\c A\\p \\v 1 text']))
self.assertRaises(SyntaxError,list,usfm.parser(['\\id TEST\\c 1 text\\p \\v 1 text']))
# Verse number parsing
self.assertRaises(SyntaxError,list,usfm.parser(['\\id TEST\\c 1\\p \\v \\p text']))
self.assertRaises(SyntaxError,list,usfm.parser(['\\id TEST\\c 1\\p \\v text']))
# Note text parsing
self.assertRaises(SyntaxError,list,usfm.parser(['\\id TEST\\mt \\f \\fk key\\fk* text.\\f*']))
def test_reference(self):
p = flatten(
usfm.decorate_references(
usfm.parser('\\id MAT EN\n\\c 1\n\\p\n\\v 1 \\v 2-3\n'
'\\id JHN DE\n\\c 3\n\\p\n\\v 16'.splitlines())))
self.assertEqual(
[(*e.pos, e.pos.book, e.pos.chapter, e.pos.verse, str(e)) for e in p],
[(1, 1, 'MAT', None, None, '\\id'),
(1, 5, 'MAT', None, None, 'MAT EN'),
(2, 1, 'MAT', '1', None, '\\c 1'),
(3, 1, 'MAT', '1', None, '\\p'),
(4, 1, 'MAT', '1', '1', '\\v 1 '),
(4, 6, 'MAT', '1', '2-3', '\\v 2-3 '),
(5, 1, 'JHN', None, None, '\\id'),
(5, 5, 'JHN', None, None, 'JHN DE'),
(6, 1, 'JHN', '3', None, '\\c 3'),
(7, 1, 'JHN', '3', None, '\\p'),
(8, 1, 'JHN', '3', '16', '\\v 16 ')])
else:
opts.tags = range(1, len(args))
else:
opts.tags = [tag.strip() for tag in opts.tags.split(', ')]
output = codecs.open(os.path.expanduser(args[0]),
mode='w',
encoding='utf_8_sig')
paths = chain.from_iterable(map(glob.iglob, args[1:]))
files = (codecs.open(p, mode='r', encoding='utf_8_sig') for p in paths)
try:
with warnings.catch_warnings():
warnings.simplefilter("always" if opts.warnings else "ignore",
SyntaxWarning)
docs = [
list(
usfm.parser(stylesheet=opts.stylesheet,
error_level=opts.error_level)) for f in files
]
validate_structure(*docs)
output.write(sfm.generate(merge(opts.tags, *docs)))
except IOError as err:
sys.stderr.write(
parser.expand_prog_name(f'%prog: IO error: {err!s}\n'))
sys.exit(2)
except StructureError:
sys.stderr.write(
parser.expand_prog_name(
'%prog: Structure error: A USFM file does not match the others\n'
))
sys.exit(3)
def test_endmarker_is_prefix(self):
self.assertEqual(list(usfm.parser(['\\id TEST\\mt \\f + text\\f*suffixed text'])), [elem('id', text('TEST'), elem('mt', elem(('f','+'), text('text')), text('suffixed text')))])
self.assertEqual(list(usfm.parser(['\\id TEST\\mt \\f + \\fr ref \\ft text\\f*suffixed text'])), [elem('id', text('TEST'), elem('mt', elem(('f','+'), elem('fr', text('ref ')), text('text')), text('suffixed text')))])
def test_sytax_error(self):
self.assertRaises(SyntaxError,list,usfm.parser(['\\id TEST\\mt text\\f*']))
self.assertRaises(SyntaxError,list,usfm.parser(['\\id TEST \\p 1 text']))
self.assertRaises(SyntaxError,list,usfm.parser(['\\id TEST\\mt \\f + text\\fe*']))
self.assertRaises(SyntaxError,list,usfm.parser(['\\id TEST\\mt \\f + text']))