def process_glyphs_directory(glyphs_directory, output_dir):
aomr_opts = {
'staff_finder': 0,
'lines_per_staff': 4,
'staff_removal': 0,
'binarization': 0,
'discard_size': 12
}
print "Processing glyphs directory"
for dirpath, dirnames, filenames in os.walk(glyphs_directory):
for f in filenames:
if f == 'page_glyphs.xml':
folder_no = os.path.basename(dirpath)
pnum = int(folder_no)
input_filename = os.path.join(dirpath, f)
lg.debug("Input filename is {0}".format(input_filename))
output_filename = os.path.join(output_dir, folder_no.zfill(4), f)
lg.debug("Output filename is {0}".format(output_filename))
shutil.copy(input_filename, output_filename)
original_image = os.path.join(output_dir, folder_no.zfill(4), 'original_image.tiff')
mei_file_write = os.path.join(output_dir, folder_no.zfill(4), 'liber-usualis-{0}.mei'.format(folder_no.zfill(4)))
glyphs = gamera_xml.glyphs_from_xml(output_filename)
aomr_obj = AomrObject(original_image, **aomr_opts)
data = aomr_obj.run(glyphs)
mei_file = AomrMeiOutput.AomrMeiOutput(data, original_image.split('/')[-2], page_number = pnum)
meitoxml.meitoxml(mei_file.md, mei_file_write)
def main(original_file, page_file, outdir):
aomr_opts = {
'lines_per_staff': 4,
'staff_finder': 0, # 0: Miyao
'staff_removal': 0,
'binarization': 0,
'discard_size': 12
}
#FILES TO PROCESS
glyphs = gamera_xml.glyphs_from_xml(page_file)
lg.debug("Original file: {0}, page file: {1}".format(original_file, page_file))
page_number = int(original_file.split('/')[-2])
fname = os.path.splitext(original_file.split('/')[-1])[0] + ".mei"
file_name = "{0}_{1}".format(page_number, fname)
# CREATING AOMR OBJECT, FINDING STAVES, AND RETRIEVING STAFF COORDINATES
aomr_obj = AomrObject(original_file, **aomr_opts)
st_position = aomr_obj.find_staves() # staves position
staff_coords = aomr_obj.staff_coords()
sorted_glyphs = aomr_obj.miyao_pitch_find(glyphs)
# PITCH FINDING
# pitch_find = aomr_obj.pitch_find(glyphs, st_position, aomr_opts.get('discard_size'))
# print len(pitch_find)
# sorted_glyphs = sorted(proc_glyphs, key=itemgetter(1, 2))
# STRUCTURING THE DATA IN JSON
data = {}
for s, stave in enumerate(staff_coords):
contents = []
for glyph, staff, offset, strt_pos, note, octave, clef_pos, clef in sorted_glyphs:
glyph_id = glyph.get_main_id()
# lg.debug("Glyph ID: {0}".format(glyph_id))
glyph_type = glyph_id.split(".")[0]
glyph_form = glyph_id.split(".")[1:]
# lg.debug("sg[1]:{0} s:{1} sg{2}".format(sg[1], s+1, sg))
# structure: g, stave, g.offset_x, note, strt_pos
if staff == s+1:
j_glyph = { 'type': glyph_type,
'form': glyph_form,
'coord': [glyph.offset_x, glyph.offset_y, glyph.offset_x + glyph.ncols, glyph.offset_y + glyph.nrows],
'strt_pitch': note,
'octv': octave,
'strt_pos': strt_pos,
'clef_pos': clef_pos,
'clef': clef}
contents.append(j_glyph)
data[s] = {'coord':stave, 'content':contents}
#print data
# CREATING THE MEI FILE
mei_file = AomrMeiOutput.AomrMeiOutput(data, file_name, page_number)
meitoxml.meitoxml(mei_file.md, os.path.join(outdir, file_name))
def create_mei_files(outdir):
aomr_opts = {
'staff_finder': 0,
'lines_per_staff': 4,
'staff_removal': 0,
'binarization': 0,
'discard_size': 12
}
for dirpath, dirnames, filenames in os.walk(outdir):
if dirpath == outdir:
continue
if ".git" in dirpath.split("/"):
continue
folder_no = os.path.basename(dirpath)
pnum = int(folder_no)
# if not "bad_{0}_corr_page_glyphs.xml".format(folder_no.zfill(4)) in filenames:
# continue
lg.debug("Generating MEI file for {0}".format(pnum))
if "{0}_corr_page_glyphs.xml".format(folder_no.zfill(4)) in filenames:
glyphs = gamera_xml.glyphs_from_xml(os.path.join(dirpath, "{0}_corr_page_glyphs.xml".format(folder_no.zfill(4))))
elif "{0}_uncorr_page_glyphs.xml".format(folder_no.zfill(4)) in filenames:
glyphs = gamera_xml.glyphs_from_xml(os.path.join(dirpath, "{0}_uncorr_page_glyphs.xml".format(folder_no.zfill(4))))
else:
lg.debug("There was no page glyphs file for page {0}".format(pnum))
continue
original_image = os.path.join(dirpath, "{0}_staves_only.tiff".format(folder_no.zfill(4)))
mei_file_write = os.path.join(dirpath, '{0}_uncorr.mei'.format(folder_no.zfill(4)))
aomr_obj = AomrObject(original_image, **aomr_opts)
try:
data = aomr_obj.run(glyphs)
except OverflowError, e:
lg.debug("Could not do detection on {0} because {1}".format(pnum, e))
continue
if not data:
# no data was returned.
lg.debug("No data was found for {0}".format(pnum))
continue
mei_file = AomrMeiOutput.AomrMeiOutput(data, "{0}_original_image.tiff".format(pnum), page_number = pnum)
meitoxml.meitoxml(mei_file.md, mei_file_write)
for i, n in enumerate(self.glyph['form']):
if n == ntype:
j = copy.copy(i) - 1
if j == 0:
idxarray.append(0)
while j:
if self.__is_valid_note_indicator(self.glyph['form'][j]):
idxarray.append(j)
break
else:
j -= 1
def __is_valid_note_indicator(self, form):
# used to test if a form is a valid indicator of a note (and not a q, dot, or anything else)
if form.isdigit():
return True
elif len(form) == 2 and form.startswith("u") or form.startswith("d"):
return True
else:
return False
if __name__ == "__main__":
v = AomrMeiOutput(test_data, 'foo..jpg')
from pymei.Export import meitoxml
meitoxml.meitoxml(v.md, 'testfile.mei')
# [1] http://wwvv.newadvent.org/cathen/10765b.htm; Some of the liquescent
# neums have special names. Thus the liquescent podatus is called epiphonus,
# the liquescent clivis, cephalicus, the liquescent climacus, ancus.
def __note_addition_figurer_outer(self, ntype, idxarray):
for i,n in enumerate(self.glyph['form']):
if n == ntype:
j = copy.copy(i) - 1
if j == 0:
idxarray.append(0)
while j:
if self.__is_valid_note_indicator(self.glyph['form'][j]):
idxarray.append(j)
break
else:
j -= 1
def __is_valid_note_indicator(self, form):
# used to test if a form is a valid indicator of a note (and not a q, dot, or anything else)
if form.isdigit():
return True
elif len(form) == 2 and form.startswith("u") or form.startswith("d"):
return True
else:
return False
if __name__ == "__main__":
v = AomrMeiOutput(test_data, 'foo..jpg')
from pymei.Export import meitoxml
meitoxml.meitoxml(v.md, 'testfile.mei')
# [1] http://wwvv.newadvent.org/cathen/10765b.htm; Some of the liquescent
# neums have special names. Thus the liquescent podatus is called epiphonus,
# the liquescent clivis, cephalicus, the liquescent climacus, ancus.
from pymei.Helpers import template
from pymei.Export import meitoxml
d = template.create('mix')
meitoxml.meitoxml(d, 'yum.mei')
mei.add_children([meihead, music])
meifile.addelement(mei)
return meifile
# import hocr and mei files into lists and strip extension where useful
hocrfiles=[x.split('.')[0] for x in glob.glob('????.html')]
allmeifiles=glob.glob('*.mei')
meifiles=[x.split('_')[0] for x in allmeifiles]
# for each hocr file: if corresponding mei file exists, open mei and edit - if not, create new mei
if options.corrected:
for hocrfile in hocrfiles:
output_name='%s_corr.mei' % (hocrfile,) if '%s_corr.mei' % (hocrfile,) in allmeifiles else '%s_uncorr.mei' % (hocrfile,)
meifile=xmltomei.xmltomei(output_name) if hocrfile in meifiles else create_mei(hocrfile)
surface=meifile.search('surface')[0]
section=meifile.search('section')[0]
add_text_lines(hocrfile, surface, section)
meitoxml.meitoxml(meifile, '../mei_corrtxt/%s' % (output_name,))
else:
for hocrfile in hocrfiles:
meifile=MeiDocument.MeiDocument()
mei=mod.mei_()
surface=mod.surface_()
section=mod.section_()
mei.add_children([surface, section])
add_text_lines(hocrfile, surface, section)
meifile.addelement(mei)
meitoxml.meitoxml(meifile, '../mei_uncorrtxt/%s_mei_fragment.mei' % (hocrfile,))
"strt_pitch": "E",
"strt_pos": 5,
},
{
"type": "neume",
"form": ["torculus", "2", "4"],
"coord": [213, 179, 26, 35],
"strt_pitch": "B",
"strt_pos": 5,
},
],
},
2: {
"coord": [4, 5, 6, 7],
"content": [{"type": "", "form": [], "coord": [], "strt_pitch": "A", "strt_pos": ""}],
},
}
v = GameraMeiOutput(test_data)
from pymei.Export import meitoxml
meitoxml.meitoxml(v.md, "testfile.mei")
# pdb.set_trace()
# [1] http://wwvv.newadvent.org/cathen/10765b.htm; Some of the liquescent
# neums have special names. Thus the liquescent podatus is called epiphonus,
# the liquescent clivis, cephalicus, the liquescent climacus, ancus.
