def test_get_id_for_idx(self):
xuwc = XUWc()
region_id = "file1.1.4"
self.assertEqual( "file1", xuwc.get_id_for_idx( 0, region_id) )
self.assertEqual( "file1.1", xuwc.get_id_for_idx(1, region_id))
self.assertEqual( "file1.1.4", xuwc.get_id_for_idx(2, region_id))
# not sure if this behavior is most useful
self.assertEqual( None, xuwc.get_id_for_idx( 3, region_id))
def test_get_ids_for_idx(self):
xuwc = XUWc()
region_ids = [ "file1.1.4", "file1.2.3", "file2.1.1" ]
new_ids = xuwc.get_ids_for_idx( 0, region_ids )
self.assertEqual( len(new_ids), 2 )
self.assertEqual( new_ids[0], "file1" )
self.assertEqual( new_ids[1], "file2" )
new_ids = xuwc.get_ids_for_idx( 1, region_ids )
self.assertEqual( len(new_ids), 3 )
self.assertEqual( new_ids[0], "file1.1" )
self.assertEqual( new_ids[1], "file1.2" )
self.assertEqual( new_ids[2], "file2.1" )
new_ids = xuwc.get_ids_for_idx( 2, region_ids )
self.assertEqual( len(new_ids), 3 )
for i in range(0, len(region_ids)):
self.assertEqual( region_ids[i], new_ids[i] )
# not sure if this behavior is most useful
new_ids = xuwc.get_ids_for_idx( 3, region_ids )
self.assertEqual( len(new_ids), 0 )
def test_xuwc(self):
# M 1.1: First test out some queries where I specify no options
xupath = self.tei_xupath1
file_paths = [ self.tei_data_path1 ]
count_unit = TEIXMLGrammar.SECTION
container_unit = BuiltinGrammar.FILE
label_path_delimiter = ":"
element_equality_fields = [ CorpusElement.LABEL_PATH,\
CorpusElement.LANGUAGE_NAME_PATH,\
CorpusElement.TEXT ]
xuwc = XUWc.create(xupath, file_paths, element_equality_fields, count_unit, container_unit, label_path_delimiter)
self.assertEqual( xuwc.get_container_unit(), BuiltinGrammar.FILE )
#container_corpus = xuwc.get_container_corpus()
#self.assertEqual( len(container_corpus), 1)
#container_idx = 0
#self.assertEqual( container_corpus[container_idx].get_file_path(), self.tei_data_path1 )
self.assertEqual( xuwc.get_count_unit(), TEIXMLGrammar.SECTION )
counts = xuwc.get_counts()
key = os.path.basename(self.tei_data_path1)
self.assertEqual( counts[key], 2 )
# M 1.2
xupath = self.tei_xupath2
file_paths = [ self.tei_data_path1, self.tei_data_path2 ]
count_unit = TEIXMLGrammar.SUBSUBSECTION
container_unit = BuiltinGrammar.FILE
label_path_delimiter = ":"
xuwc = XUWc.create(xupath, file_paths, element_equality_fields, count_unit, container_unit, label_path_delimiter)
self.assertEqual( xuwc.get_container_unit(), BuiltinGrammar.FILE )
self.assertEqual( xuwc.get_count_unit(), TEIXMLGrammar.SUBSUBSECTION )
counts = xuwc.get_counts()
# There is only one subsubsection with 'Globus' in it and its in v1
self.assertEqual( len(counts.keys()), 2 )
key = os.path.basename(self.tei_data_path1)
self.assertEqual( counts[key], 1 )
# M 2.1 Override count
xupath = self.ios_xupath1
file_paths = [ self.ios_data_path1 ]
count_unit = BuiltinGrammar.BYTE
container_unit = CiscoIOSGrammar.INTERFACE
label_path_delimiter = ":"
xuwc = XUWc.create(xupath, file_paths, element_equality_fields, count_unit, container_unit, label_path_delimiter)
self.assertEqual( xuwc.get_container_unit(), CiscoIOSGrammar.INTERFACE )
self.assertEqual( xuwc.get_count_unit(), BuiltinGrammar.BYTE )
counts = xuwc.get_counts()
self.assertEqual( len(counts.keys()), 2 )
key1 = label_path_delimiter.join(["router.v1.example", "Loopback0"])
key2 = label_path_delimiter.join(["router.v1.example", "GigabitEthernet4/2"])
self.assertEqual( counts[key1], 186 )
self.assertEqual( counts[key2], 232 )
# M 2.3
xupath = self.ios_xupath1
file_paths = [ self.ios_data_path1 ]
count_unit = BuiltinGrammar.WORD
container_unit = CiscoIOSGrammar.INTERFACE
label_path_delimiter = ":"
xuwc = XUWc.create(xupath, file_paths, element_equality_fields, count_unit, container_unit, label_path_delimiter)
self.assertEqual( xuwc.get_container_unit(), CiscoIOSGrammar.INTERFACE )
self.assertEqual( xuwc.get_count_unit(), BuiltinGrammar.WORD )
counts = xuwc.get_counts()
key1 = label_path_delimiter.join(["router.v1.example", "Loopback0"])
key2 = label_path_delimiter.join(["router.v1.example", "GigabitEthernet4/2"])
self.assertEqual( counts[key1], 23 )
self.assertEqual( counts[key2], 27 )
# M 2.4
xupath = self.ios_xupath1
file_paths = [ self.ios_data_path1 ]
count_unit = BuiltinGrammar.CHARACTER
container_unit = CiscoIOSGrammar.INTERFACE
label_path_delimiter = ":"
xuwc = XUWc.create(xupath, file_paths, element_equality_fields, count_unit, container_unit, label_path_delimiter)
self.assertEqual( xuwc.get_container_unit(), CiscoIOSGrammar.INTERFACE )
self.assertEqual( xuwc.get_count_unit(), BuiltinGrammar.CHARACTER )
counts = xuwc.get_counts()
key1 = label_path_delimiter.join(["router.v1.example", "Loopback0"])
key2 = label_path_delimiter.join(["router.v1.example", "GigabitEthernet4/2"])
self.assertEqual( counts[key1], 186 )
self.assertEqual( counts[key2], 232 )
"""
# M 2.6
# This is a case that we don't yet implement AND
# to query number of subsections that satisfy, we need a predicate
xupath = "/".join( [ TEIXMLGrammar.SECTION, TEIXMLGrammar.SUBSECTION, TEIXMLGrammar.SUBSUBSECTION ] )
file_paths = [ self.tei_data_path1 ]
count_unit = TEIXMLGrammar.SUBSECTION
container_unit = BuiltinGrammar.FILE
label_path_delimiter = ":"
xuwc = XUWc.create(xupath, file_paths, count_unit, container_unit, label_path_delimiter)
self.assertEqual( xuwc.get_container_unit(), BuiltinGrammar.FILE )
self.assertEqual( xuwc.get_count_unit(), TEIXMLGrammar.SUBSECTION )
counts = xuwc.get_counts()
label_path_keys = counts.keys()
self.assertEqual( len(label_path_keys), 1 )
key = label_path_keys[0]
self.assertEqual( counts[key], 1 )
"""
# M 4.1
xupath = "/".join( [ TEIXMLGrammar.SECTION, TEIXMLGrammar.PARAGRAPH ] )
file_paths = [ self.tei_data_path1 ]
count_unit = TEIXMLGrammar.PARAGRAPH
container_unit = TEIXMLGrammar.SECTION
label_path_delimiter = ":"
xuwc = XUWc.create(xupath, file_paths, element_equality_fields, count_unit, container_unit, label_path_delimiter)
self.assertEqual( xuwc.get_container_unit(), TEIXMLGrammar.SECTION )
self.assertEqual( xuwc.get_count_unit(), TEIXMLGrammar.PARAGRAPH )
counts = xuwc.get_counts()
## There are two sections
self.assertEqual( len(counts.keys()), 2 )
key1 = label_path_delimiter.join(["section.tei.v1.xml", "1 INTRODUCTION"])
key2 = label_path_delimiter.join(["section.tei.v1.xml", "9. Glossary"])
# should be 4 and not 5 since the paragraphs in subsubsection2 are the same
# under our base equality function
self.assertEqual( counts[key1], 4)
self.assertEqual( counts[key2], 1)
"""
# M 4.4 I'm not sure what this test even means
xupath = "/".join([ TEIXMLGrammar.SECTION, TEIXMLGrammar.PARAGRAPH ] )
file_paths = [ self.tei_data_path1 ]
count_unit = TEIXMLGrammar.PARAGRAPH
container_unit = TEIXMLGrammar.PARAGRAPH
label_path_delimiter = ":"
xuwc = XUWc.create(xupath, file_paths, count_unit, container_unit, label_path_delimiter)
self.assertEqual( xuwc.get_container_unit(), TEIXMLGrammar.PARAGRAPH )
self.assertEqual( xuwc.get_count_unit(), TEIXMLGrammar.PARAGRAPH )
counts = xuwc.get_counts()
print counts.keys()
self.assertEqual( len(counts.keys()), 6 )
"""
# M 4.5
xupath = "/".join([ TEIXMLGrammar.SECTION, TEIXMLGrammar.SUBSECTION, TEIXMLGrammar.PARAGRAPH] )
file_paths = [ self.tei_data_path1 ]
count_unit = TEIXMLGrammar.PARAGRAPH
container_unit = TEIXMLGrammar.SUBSECTION
label_path_delimiter = ":"
xuwc = XUWc.create(xupath, file_paths, element_equality_fields, count_unit, container_unit, label_path_delimiter)
self.assertEqual( xuwc.get_container_unit(), TEIXMLGrammar.SUBSECTION )
self.assertEqual( xuwc.get_count_unit(), TEIXMLGrammar.PARAGRAPH )
counts = xuwc.get_counts()
self.assertEqual( len(counts.keys()), 1)
key = counts.keys()[0]
self.assertEqual( counts[key], 3 )
# M 4.6
xupath = "/".join([ TEIXMLGrammar.SECTION, TEIXMLGrammar.SUBSECTION, TEIXMLGrammar.PARAGRAPH] )
file_paths = [ self.tei_data_path1 ]
count_unit = TEIXMLGrammar.PARAGRAPH
container_unit = TEIXMLGrammar.SECTION
label_path_delimiter = ":"
xuwc = XUWc.create(xupath, file_paths, element_equality_fields, count_unit, container_unit, label_path_delimiter)
self.assertEqual( xuwc.get_container_unit(), TEIXMLGrammar.SECTION )
self.assertEqual( xuwc.get_count_unit(), TEIXMLGrammar.PARAGRAPH )
counts = xuwc.get_counts()
# There is only 1 section that contains a subsection
self.assertEqual( len(counts.keys()), 1)
key = counts.keys()[0]
# There are 3 paragraphs contained within the subsection
self.assertEqual( counts[key], 3 )
# M 4.7
xupath = "/".join([ TEIXMLGrammar.SECTION, TEIXMLGrammar.PARAGRAPH ] )
file_paths = [ self.tei_data_path1 ]
count_unit = TEIXMLGrammar.PARAGRAPH
container_unit = TEIXMLGrammar.SECTION
label_path_delimiter = ":"
xuwc = XUWc.create(xupath, file_paths, element_equality_fields, count_unit, container_unit, label_path_delimiter)
self.assertEqual( xuwc.get_container_unit(), TEIXMLGrammar.SECTION )
self.assertEqual( xuwc.get_count_unit(), TEIXMLGrammar.PARAGRAPH )
counts = xuwc.get_counts()
self.assertEqual( len(counts.keys()), 2)
key1 = label_path_delimiter.join( ["section.tei.v1.xml","1 INTRODUCTION"] )
key2 = label_path_delimiter.join( ["section.tei.v1.xml","9. Glossary"] )
self.assertEqual( counts[key1], 4)
self.assertEqual( counts[key2], 1)
# M 4.8
xupath = "/".join([ TEIXMLGrammar.SECTION, TEIXMLGrammar.PARAGRAPH, BuiltinGrammar.LINE ] )
file_paths = [ self.tei_data_path1 ]
count_unit = TEIXMLGrammar.PARAGRAPH
container_unit = BuiltinGrammar.LINE
label_path_delimiter = ":"
with self.assertRaises(IndexError):
xuwc = XUWc.create(xupath, file_paths, element_equality_fields, count_unit, container_unit, label_path_delimiter)
p = optparse.OptionParser()
p.add_option("-a", "--count", dest="count_type")
p.add_option("-b", "--re_count", dest="count_regexp")
p.add_option("-c", "--context", dest="context_type")
p.add_option("-d", "--re_context", dest="context_regexp")
(options, args) = p.parse_args()
if ( len(args) < 2 ):
print "Usage xuwc [ --count <count_type> | --re_count <count_regexp> ] [ --context <context_type> | --re_context <context_regexp> ] <xpath> <files>+"
sys.exit(0)
xpath = args[0]
file_paths = args[1:]
wc_params = {}
wc_params['count_type'] = options.count_type
wc_params['count_regexp'] = options.count_regexp
wc_params['context_type'] = options.context_type
wc_params['context_regexp'] = options.context_regexp
if wc_params['count_type'] != None and wc_params['count_regexp'] != None:
print "Cannot specify both a count and re_count option."
sys.exit(-1)
if wc_params['context_type'] != None and wc_params['context_regexp'] != None:
print "Cannot specify both a context and re_context option."
sys.exit(-1)
wc_reports = XUWc.xuwc_main( xpath, file_paths, wc_params )
XUWc.output_reports( wc_reports, wc_params )
def test_xuwc(self):
# M 1.1: First test out the some queries when I specify no options
xpath = "//tei:section"
file_paths = [ self.tei_data_path1 ]
wc_params = {}
wc_params['count_type'] = None
wc_params['count_regexp'] = None
wc_params['context_type'] = None
wc_params['context_regexp'] = None
wc_reports = XUWc.xuwc_main( xpath, file_paths, wc_params )
self.assertEqual( len(wc_reports.keys()), 1 )
self.assertEqual( wc_reports.keys()[0], self.tei_data_path1 )
wc_report = wc_reports[ self.tei_data_path1 ]
num_context_regions = len(wc_report.keys())
self.assertEqual( num_context_regions, 1 )
self.assertEqual( wc_params['context_type'], "file_path" )
context_region_id = wc_report.keys()[0]
self.assertEqual( wc_report[context_region_id], 2 )
self.assertEqual( wc_params['count_type'], "tei:section" )
# M 1.2
xpath = "//tei:section/tei:subsection/tei:subsubsection[re:testsubtree('Globus','gi')]"
file_paths = [ self.tei_data_path1, self.tei_data_path2 ]
wc_params = {}
wc_params['count_type'] = None
wc_params['count_regexp'] = None
wc_params['context_type'] = None
wc_params['context_regexp'] = None
wc_reports = XUWc.xuwc_main( xpath, file_paths, wc_params )
self.assertEqual( len(wc_reports.keys()), 2 )
self.assertEqual( wc_reports.keys()[0], self.tei_data_path1 )
self.assertEqual( wc_reports.keys()[1], self.tei_data_path2 )
wc_report = wc_reports[ self.tei_data_path1 ]
num_context_regions = len( wc_report.keys() )
self.assertEqual( num_context_regions, 1 )
self.assertEqual( wc_params['context_type'], "file_path" )
context_region_id = wc_report.keys()[0]
self.assertEqual( wc_report[context_region_id], 1 )
self.assertEqual( wc_params['count_type'], "tei:subsubsection")
wc_report = wc_reports[ self.tei_data_path2 ]
num_context_regions = len( wc_report.keys() )
self.assertEqual( num_context_regions, 1 )
self.assertEqual( wc_params['context_type'], "file_path" )
context_region_id = wc_report.keys()[0]
self.assertEqual( wc_report[context_region_id], 1 )
self.assertEqual( wc_params['count_type'], "tei:subsubsection")
# M 2.1 Override count
xpath = "//ios:interface"
file_paths = [ self.ios_data_path1 ]
wc_params = {}
wc_params['count_type'] = "builtin:byte"
wc_params['count_regexp'] = None
wc_params['context_type'] = "ios:interface"
wc_params['context_regexp'] = None
wc_reports = XUWc.xuwc_main( xpath, file_paths, wc_params )
self.assertEqual( len(wc_reports.keys()), 1 )
self.assertEqual( wc_reports.keys()[0], self.ios_data_path1 )
wc_report = wc_reports[ self.ios_data_path1 ]
num_context_regions = len( wc_report.keys() )
self.assertEqual( num_context_regions, 2 )
self.assertEqual( wc_params['context_type'], "ios:interface" )
key_prefix = self.ios_data_path1.replace('.','_')
context_region1_id = key_prefix + ".Loopback0"
context_region2_id = key_prefix + ".GigabitEthernet4/2"
self.assertEqual( wc_report[context_region1_id], 186 )
self.assertEqual( wc_report[context_region2_id], 232 )
self.assertEqual( wc_params['count_type'], "builtin:byte" )
# M 2.3
file_paths = [ self.ios_data_path1 ]
wc_params = {}
wc_params['count_type'] = "builtin:word"
wc_params['count_regexp'] = None
wc_params['context_type'] = "ios:interface"
wc_params['context_regexp'] = None
wc_reports = XUWc.xuwc_main( xpath, file_paths, wc_params )
self.assertEqual( len(wc_reports.keys()), 1 )
self.assertEqual( wc_reports.keys()[0], self.ios_data_path1 )
wc_report = wc_reports[ self.ios_data_path1 ]
num_context_regions = len( wc_report.keys() )
self.assertEqual( num_context_regions, 2 )
self.assertEqual( wc_params['context_type'], "ios:interface" )
key_prefix = self.ios_data_path1.replace('.','_')
context_region1_id = key_prefix + ".Loopback0"
context_region2_id = key_prefix + ".GigabitEthernet4/2"
self.assertEqual( wc_report[context_region1_id], 23 )
self.assertEqual( wc_report[context_region2_id], 27 )
self.assertEqual( wc_params['count_type'], "builtin:word" )
# M 2.4
file_paths = [ self.ios_data_path1 ]
wc_params = {}
wc_params['count_type'] = "builtin:character"
wc_params['count_regexp'] = None
wc_params['context_type'] = "ios:interface"
wc_params['context_regexp'] = None
wc_reports = XUWc.xuwc_main( xpath, file_paths, wc_params )
self.assertEqual( len(wc_reports.keys()), 1 )
self.assertEqual( wc_reports.keys()[0], self.ios_data_path1 )
wc_report = wc_reports[ self.ios_data_path1 ]
num_context_regions = len( wc_report.keys() )
self.assertEqual( num_context_regions, 2 )
self.assertEqual( wc_params['context_type'], "ios:interface" )
key_prefix = self.ios_data_path1.replace('.','_')
context_region1_id = key_prefix + ".Loopback0"
context_region2_id = key_prefix + ".GigabitEthernet4/2"
self.assertEqual( wc_report[context_region1_id], 186 )
self.assertEqual( wc_report[context_region2_id], 232 )
self.assertEqual( wc_params['count_type'], "builtin:character" )
# M 2.5
# This one should generate an error
xpath = "//tei:section"
file_paths = [ self.tei_data_path1 ]
wc_params = {}
wc_params['count_type'] = "tei:subsection"
wc_params['count_regexp'] = None
wc_params['context_type'] = None
wc_params['context_regexp'] = None
#wc_reports = HWc.hwc_main( xpath, file_paths, wc_params )
# M 2.6
xpath = "//tei:section/tei:subsection/tei:subsubsection"
file_paths = [ self.tei_data_path1 ]
wc_params = {}
wc_params['count_type'] = "tei:subsection"
wc_params['count_regexp'] = None
wc_params['context_type'] = None
wc_params['context_regexp'] = None
wc_reports = XUWc.xuwc_main( xpath, file_paths, wc_params )
self.assertEqual( len(wc_reports.keys()), 1 )
self.assertEqual( wc_reports.keys()[0], self.tei_data_path1 )
wc_report = wc_reports[ self.tei_data_path1 ]
num_context_regions = len( wc_report.keys() )
self.assertEqual( num_context_regions, 1 )
self.assertEqual( wc_params['context_type'], "file_path" )
context_region_id = wc_report.keys()[0]
self.assertEqual( wc_report[context_region_id], 1 )
self.assertEqual( wc_params['count_type'], "tei:subsection" )
# M 3.1
xpath = "//tei:section"
file_paths = [ self.tei_data_path1 ]
wc_params = {}
wc_params['count_type'] = None
wc_params['count_regexp'] = "\w+"
wc_params['context_type'] = "tei:section"
wc_params['context_regexp'] = None
wc_reports = XUWc.xuwc_main( xpath, file_paths, wc_params )
self.assertEqual( len(wc_reports.keys()), 1 )
self.assertEqual( wc_reports.keys()[0], self.tei_data_path1 )
wc_report = wc_reports[ self.tei_data_path1 ]
num_context_regions = len(wc_report.keys())
self.assertEqual( num_context_regions, 2 )
self.assertEqual( wc_params['context_type'], "tei:section" )
key_prefix = self.tei_data_path1.replace('.','_')
context_region1_id = key_prefix + ".1"
context_region2_id = key_prefix + ".9"
self.assertEqual( wc_report[context_region1_id], 357 )
self.assertEqual( wc_report[context_region2_id], 45 )
self.assertEqual( wc_params['count_regexp'], "\w+" )
# M 4.1 context override
xpath = "//tei:section/tei:p"
file_paths = [ self.tei_data_path1 ]
wc_params = {}
wc_params['count_type'] = None
wc_params['count_regexp'] = None
wc_params['context_type'] = "tei:section"
wc_params['context_regexp'] = None
wc_reports = XUWc.xuwc_main( xpath, file_paths, wc_params )
self.assertEqual( len(wc_reports.keys()), 1 )
self.assertEqual( wc_reports.keys()[0], self.tei_data_path1 )
wc_report = wc_reports[ self.tei_data_path1 ]
num_context_regions = len(wc_report.keys())
self.assertEqual( num_context_regions, 2 )
self.assertEqual( wc_params['context_type'], "tei:section" )
section1_context_region_id = wc_report.keys()[0]
section2_context_region_id = wc_report.keys()[1]
self.assertEqual( wc_report[ section1_context_region_id ], 5 )
self.assertEqual( wc_report[ section2_context_region_id ], 1 )
self.assertEqual( wc_params['count_type'], "tei:p" )
# M 4.2 should generate an error
xpath = "//tei:section/tei:p"
file_paths = [ self.tei_data_path1 ]
wc_params = {}
wc_params['count_type'] = None
wc_params['count_regexp'] = None
wc_params['context_type'] = "tei:subsection"
wc_params['context_regexp'] = None
#wc_reports = HWc.hwc_main( xpath, file_paths, wc_params )
# M 4.3 should generate an error
xpath = "//tei:section/tei:subsection"
file_paths = [ self.tei_data_path1 ]
wc_params = {}
wc_params['count_type'] = None
wc_params['count_regexp'] = None
wc_params['context_type'] = "tei:subsubsection"
wc_params['context_regexp'] = None
#wc_reports = HWc.hwc_main( xpath, file_paths, wc_params )
# M 4.4
xpath = "//tei:section/tei:p"
file_paths = [ self.tei_data_path1 ]
wc_params = {}
wc_params['count_type'] = None
wc_params['count_regexp'] = None
wc_params['context_type'] = "tei:p"
wc_params['context_regexp'] = None
wc_reports = XUWc.xuwc_main( xpath, file_paths, wc_params )
self.assertEqual( len(wc_reports.keys()), 1 )
self.assertEqual( wc_reports.keys()[0], self.tei_data_path1 )
wc_report = wc_reports[ self.tei_data_path1 ]
num_context_regions = len(wc_report.keys())
self.assertEqual( num_context_regions, 6 )
self.assertEqual( wc_params['context_type'], "tei:p" )
for context_region_id in wc_report.keys():
self.assertEqual( wc_report[context_region_id], 1 )
self.assertEqual( wc_params['count_type'], "tei:p" )
# M 4.5
xpath = "//tei:section/tei:subsection/tei:p"
file_paths = [ self.tei_data_path1 ]
wc_params = {}
wc_params['count_type'] = None
wc_params['count_regexp'] = None
wc_params['context_type'] = "tei:subsection"
wc_params['context_regexp'] = None
wc_reports = XUWc.xuwc_main( xpath, file_paths, wc_params )
self.assertEqual( len(wc_reports.keys()), 1 )
self.assertEqual( wc_reports.keys()[0], self.tei_data_path1 )
wc_report = wc_reports[ self.tei_data_path1 ]
num_context_regions = len( wc_report.keys() )
self.assertEqual( num_context_regions, 1 )
self.assertEqual( wc_params['context_type'], "tei:subsection")
section1_context_region_id = wc_report.keys()[0]
self.assertEqual( wc_report[ section1_context_region_id ], 4 )
self.assertEqual( wc_params['count_type'], "tei:p" )
# M 4.6
xpath = "//tei:section/tei:subsection/tei:p"
file_paths = [ self.tei_data_path1 ]
wc_params = {}
wc_params['count_type'] = None
wc_params['count_regexp'] = None
wc_params['context_type'] = "tei:section"
wc_params['context_regexp'] = None
wc_reports = XUWc.xuwc_main( xpath, file_paths, wc_params )
self.assertEqual( len(wc_reports.keys()), 1 )
self.assertEqual( wc_reports.keys()[0], self.tei_data_path1 )
wc_report = wc_reports[ self.tei_data_path1 ]
num_context_regions = len( wc_report.keys() )
self.assertEqual( num_context_regions, 1 )
self.assertEqual( wc_params['context_type'], "tei:section")
section1_context_region_id = wc_report.keys()[0]
self.assertEqual( wc_report[ section1_context_region_id ], 4 )
self.assertEqual( wc_params['count_type'], "tei:p" )
# M 4.7
xpath = "//tei:section/tei:p"
file_paths = [ self.tei_data_path1 ]
wc_params = {}
wc_params['count_type'] = None
wc_params['count_regexp'] = None
wc_params['context_type'] = "tei:section"
wc_params['context_regexp'] = None
wc_reports = XUWc.xuwc_main( xpath, file_paths, wc_params )
self.assertEqual( len( wc_reports.keys() ), 1 )
self.assertEqual( wc_reports.keys()[0], self.tei_data_path1 )
wc_report = wc_reports[ self.tei_data_path1 ]
num_context_regions = len( wc_report.keys() )
self.assertEqual( num_context_regions, 2 )
self.assertEqual( wc_params['context_type'], "tei:section")
section1_context_region_id = wc_report.keys()[0]
section9_context_region_id = wc_report.keys()[1]
self.assertEqual( wc_report[ section1_context_region_id ], 5 )
self.assertEqual( wc_report[ section9_context_region_id ], 1 )
self.assertEqual( wc_params['count_type'], "tei:p" )
# M 4.8 - should explode
xpath = "//tei:section/tei:p"
file_paths = [ self.tei_data_path1 ]
wc_params = {}
wc_params['count_type'] = None
wc_params['count_regexp'] = None
wc_params['context_type'] = None
wc_params['context_regexp'] = "builtin:line"
wc_reports = XUWc.xuwc_main( xpath, file_paths, wc_params )
