def test_Parse(self):
text = """data_no_comments_here
save_comment
_Saveframe_category comment
loop_
_comment
_every_flag
_category
'#It has very upfield-shifted H5', H5" @ 3.935,4.012 ppm'
;
#######################
# BOGUS #
#######################
;
BOGUS_CATEGORY
stop_
save_
"""
self.assertFalse(self.strf.parse(text=text))
st = self.strf.star_text()
# print "unparsed text:[" +st+ "]"
exp = """data_no_comments_here
save_comment _Saveframe_category comment loop_
_comment
_every_flag
_category
;
#It has very upfield-shifted H5', H5" @ 3.935,4.012 ppm
;
;
#######################
# BOGUS #
#######################
; BOGUS_CATEGORY stop_ save_
"""
self.assertTrue(Utils.equalIgnoringWhiteSpace(exp, st))
def test_Parse(self):
text = """data_no_comments_here
save_comment
_Saveframe_category comment
loop_
_comment
_every_flag
_category
'#It has very upfield-shifted H5', H5" @ 3.935,4.012 ppm'
;
#######################
# BOGUS #
#######################
;
BOGUS_CATEGORY
stop_
save_
"""
self.assertFalse(self.strf.parse(text = text))
st = self.strf.star_text()
# print "unparsed text:[" +st+ "]"
exp = """data_no_comments_here
save_comment _Saveframe_category comment loop_
_comment
_every_flag
_category
;
#It has very upfield-shifted H5', H5" @ 3.935,4.012 ppm
;
;
#######################
# BOGUS #
#######################
; BOGUS_CATEGORY stop_ save_
"""
self.assertTrue(Utils.equalIgnoringWhiteSpace(exp, st))
def parse (self, text='', nmrView_type = 0):
"""
- Parses text into save frames and tagtables.
- Input text should start at position given with non-white space character
- Appends a list of datanodes(save frames or tagtables)
"""
if self.verbosity > 2:
nTdebug('Parsing STAR file: %s' % self.filename)
# '"Begin at the beginning," the King said, gravely,
# "and go on till you come to the end; then stop."' (LC)
# print "DEBUG taking care of EOL variations"
text = Utils.dos2unix(text)# \r\n -> \n
text = Utils.mac2unix(text)# \r -> \n
text = comments_strip(text)
## Collapse the semicolon block for ease of parsing
text = semicolon_block_collapse(text)
## For nmrView 'nmrStar' also compress { } into {}
## Wim 05/03/2003
if nmrView_type:
text = nmrView_compress(text)
## TITLE
match_data_tag = re.search(r'\s*data_(\S+)\s+', text, 0)
if not match_data_tag:
print "ERROR: found no 'data_title' string in "
print "ERROR: file's text (first 100 chars):[%s] " % text[0:100]
return 1
self.title = match_data_tag.group(1)
pos = match_data_tag.end()
## Four quick searches for possible continuations
next_sf_begin = None # SAVE FRAME BEGIN
next_sf_end = None # SAVE FRAME END
next_free_tt = None # FREE TAGTABLE
next_loop_tt = None # LOOP TAGTABLE
sf_open = None # When a saveframe is open
text_length = len(text)
## Only break when parsed to the eof
while pos < text_length:
if self.verbosity >= 9:
print 'Parse text from position:%s : [%s]' % (
pos, text[pos:pos+10])
match_save_begin_nws = pattern_save_begin_nws.search(text, pos, pos+len('save_1'))
if match_save_begin_nws:
if match_save_begin_nws.start() == pos:
next_sf_begin = 1
if not next_sf_begin:
match_save_end_nws = pattern_save_end_nws.search(text, pos, pos+len('save_ '))
if match_save_end_nws:
if match_save_end_nws.start() == pos:
next_sf_end = 1
if not (next_sf_begin or next_sf_end):
match_tag_name_nws = pattern_tag_name_nws.search(text, pos, pos+len(' _X'))
if match_tag_name_nws:
if match_tag_name_nws.start() == pos:
next_free_tt = 1
if not (next_sf_begin or next_sf_end or next_free_tt):
match_tagtable_loop_nws = pattern_tagtable_loop_nws.search(text, pos, pos+len('loop_ '))
if match_tagtable_loop_nws:
if match_tagtable_loop_nws.start() == pos:
next_loop_tt = 1
## Just checking
if not (next_sf_begin or next_sf_end or next_free_tt or next_loop_tt):
nTerror(' No new item found in data_nodes_parse.')
print 'Items looked for are a begin or end of a saveframe, or'
print 'a begin of a tagtable(free or looped).'
print
print "At text (before pos=" , pos , "):"
start = pos-70
if start < 0:
start = 0
print "[" + text[start:pos] + "]"
print "At text (starting pos=" , pos , "):"
print "[" + text[pos:pos+70]+ "]"
return None
## SAVE FRAME BEGIN
if next_sf_begin:
if sf_open:
print "ERROR: Found the beginning of a saveframe but"
print "ERROR: saveframe before is still open(not closed;-)"
return None
match_save_begin = pattern_save_begin.search(text, pos)
if not match_save_begin:
print "ERROR: Code error (no second match on sf begin)"
return None
if match_save_begin.start() != pos:
print "ERROR: Code error (wrong second match on sf begin)"
return None
self.datanodes.append(SaveFrame(tagtables = [])) # Need resetting ?
self.datanodes[-1].title = match_save_begin.group(1)
sf_open = 1
next_sf_begin = None
pos = match_save_begin.end()
continue
## SAVE FRAME END
if next_sf_end:
if not sf_open:
print "ERROR: Found the end of a saveframe but"
print "ERROR: saveframe was not open"
return None
match_save_end = pattern_save_end.search(text, pos)
if not match_save_end:
print "ERROR: Code error (no second match on sf end)"
return None
if match_save_end.start() != pos:
print "ERROR: Code error (wrong second match on sf end)"
return None
sf_open = None
next_sf_end = None
pos = match_save_end.end()
continue
## FREE or LOOP TAGTABLE
if next_free_tt:
free = 1
next_free_tt = None
else: # next_loop_tt must be true as this was checked before
if not next_loop_tt:
nTerror(' code bug in File.parse()')
return None
free = None
next_loop_tt = None
match_tagtable_loop = pattern_tagtable_loop.search(text, pos)
if not match_tagtable_loop:
nTerror(' Code error, no second match on tagtable_loop')
return None
if match_tagtable_loop.start() != pos:
print "ERROR: Code error (wrong second match on tagtable_loop)"
return None
pos = match_tagtable_loop.end()
if sf_open:
dn = self.datanodes[-1].tagtables # Insert in last saveframes' tagtables
else:
dn = self.datanodes
dn.append(
TagTable(free = free,
tagnames = [],
tagvalues = [],
verbosity = self.verbosity))
tt = dn[-1] # Just to be explicit for the beloved reader
pos = tt.parse(text=text, pos=pos)
if pos == None:
print "ERROR: In parsing tagtable"
return None
if self.verbosity >=9:
print 'Parsed tagtable up to pos: [%s]' % pos
if self.verbosity > 2:
print 'DEBUG Parsed: [%s] datanodes (top level count only)' % \
len(self.datanodes)
if self.check_integrity(recursive = 0):
print "ERROR: integrity not ok"
return 1
# Save some memory
text = ''
return 0