Recached

24964326097

Committed 26 Apr 2026 06:49PM UTC coverage: 0.0% (-67.4%) from 67.38%

Build # 24964326097

Build Type

push

github

Committed by

web-flow

Commit Message

Merge pull request #479 from afuetterer/docs-requirements

build(deps): add dependency-groups

Coverage Stats

0 of 561 relevant lines covered (0.0%)

0.0 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

0.0

/tika/parser.py

# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements.  See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License.  You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#

import json

from .tika import ServerEndpoint, callServer, parse1


def from_file(filename, serverEndpoint=ServerEndpoint, service='all', xmlContent=False, headers=None, config_path=None, requestOptions={}, raw_response=False):
    '''
    Parses a file for metadata and content
    :param filename: path to file which needs to be parsed or binary file using open(path,'rb')
    :param serverEndpoint: Server endpoint url
    :param service: service requested from the tika server
                    Default is 'all', which results in recursive text content+metadata.
                    'meta' returns only metadata
                    'text' returns only content
    :param xmlContent: Whether or not XML content be requested.
                    Default is 'False', which results in text content.
    :param headers: Request headers to be sent to the tika reset server, should
                    be a dictionary. This is optional
    :return: dictionary having 'metadata' and 'content' keys.
            'content' has a str value and metadata has a dict type value.
    '''
    if not xmlContent:
        output = parse1(service, filename, serverEndpoint, headers=headers, config_path=config_path, requestOptions=requestOptions)
    else:
        output = parse1(service, filename, serverEndpoint, services={'meta': '/meta', 'text': '/tika', 'all': '/rmeta/xml'},
                            headers=headers, config_path=config_path, requestOptions=requestOptions)
    if raw_response:
        return output
    else:
        return _parse(output, service)


def from_buffer(string, serverEndpoint=ServerEndpoint, xmlContent=False, headers=None, config_path=None, requestOptions={}, raw_response=False):
    '''
    Parses the content from buffer
    :param string: Buffer value
    :param serverEndpoint: Server endpoint. This is optional
    :param xmlContent: Whether or not XML content be requested.
                    Default is 'False', which results in text content.
    :param headers: Request headers to be sent to the tika reset server, should
                    be a dictionary. This is optional
    :return:
    '''
    headers = headers or {}
    headers.update({'Accept': 'application/json'})

    if not xmlContent:
        status, response = callServer('put', serverEndpoint, '/rmeta/text', string, headers, False, config_path=config_path, requestOptions=requestOptions)
    else:
        status, response = callServer('put', serverEndpoint, '/rmeta/xml', string, headers, False, config_path=config_path, requestOptions=requestOptions)

    if raw_response:
        return (status, response)
    else:
        return _parse((status,response))

def _parse(output, service='all'):
    '''
    Parses response from Tika REST API server
    :param output: output from Tika Server
    :param service: service requested from the tika server
                    Default is 'all', which results in recursive text content+metadata.
                    'meta' returns only metadata
                    'text' returns only content
    :return: a dictionary having 'metadata' and 'content' values
    '''
    parsed={'metadata': None, 'content': None}
    if not output:
        return parsed

    parsed["status"] = output[0]
    if output[1] is None or output[1] == "":
        return parsed

    if service == "text":
        parsed["content"] = output[1]
        return parsed

    realJson = json.loads(output[1])

    parsed["metadata"] = {}
    if service == "meta":
        for key in realJson:
            parsed["metadata"][key] = realJson[key]
        return parsed

    content = ""
    for js in realJson:
        if "X-TIKA:content" in js:
            content += js["X-TIKA:content"]

    if content == "":
        content = None

    parsed["content"] = content

    for js in realJson:
        for n in js:
            if n != "X-TIKA:content":
                if n in parsed["metadata"]:
                    if not isinstance(parsed["metadata"][n], list):
                        parsed["metadata"][n] = [parsed["metadata"][n]]
                    parsed["metadata"][n].append(js[n])
                else:
                    parsed["metadata"][n] = js[n]

    return parsed

1	# Licensed to the Apache Software Foundation (ASF) under one or more
2	# contributor license agreements. See the NOTICE file distributed with
3	# this work for additional information regarding copyright ownership.
4	# The ASF licenses this file to You under the Apache License, Version 2.0
5	# (the "License"); you may not use this file except in compliance with
6	# the License. You may obtain a copy of the License at
7	#
8	# http://www.apache.org/licenses/LICENSE-2.0
9	#
10	# Unless required by applicable law or agreed to in writing, software
11	# distributed under the License is distributed on an "AS IS" BASIS,
12	# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13	# See the License for the specific language governing permissions and
14	# limitations under the License.
15	#
16
17	import json	×
18
19	from .tika import ServerEndpoint, callServer, parse1	×
20
21
22	def from_file(filename, serverEndpoint=ServerEndpoint, service='all', xmlContent=False, headers=None, config_path=None, requestOptions={}, raw_response=False):	×
23	'''
24	Parses a file for metadata and content
25	:param filename: path to file which needs to be parsed or binary file using open(path,'rb')
26	:param serverEndpoint: Server endpoint url
27	:param service: service requested from the tika server
28	Default is 'all', which results in recursive text content+metadata.
29	'meta' returns only metadata
30	'text' returns only content
31	:param xmlContent: Whether or not XML content be requested.
32	Default is 'False', which results in text content.
33	:param headers: Request headers to be sent to the tika reset server, should
34	be a dictionary. This is optional
35	:return: dictionary having 'metadata' and 'content' keys.
36	'content' has a str value and metadata has a dict type value.
37	'''
38	if not xmlContent:	×
39	output = parse1(service, filename, serverEndpoint, headers=headers, config_path=config_path, requestOptions=requestOptions)	×
40	else:
41	output = parse1(service, filename, serverEndpoint, services={'meta': '/meta', 'text': '/tika', 'all': '/rmeta/xml'},	×
42	headers=headers, config_path=config_path, requestOptions=requestOptions)
43	if raw_response:	×
44	return output	×
45	else:
46	return _parse(output, service)	×
47
48
49	def from_buffer(string, serverEndpoint=ServerEndpoint, xmlContent=False, headers=None, config_path=None, requestOptions={}, raw_response=False):	×
50	'''
51	Parses the content from buffer
52	:param string: Buffer value
53	:param serverEndpoint: Server endpoint. This is optional
54	:param xmlContent: Whether or not XML content be requested.
55	Default is 'False', which results in text content.
56	:param headers: Request headers to be sent to the tika reset server, should
57	be a dictionary. This is optional
58	:return:
59	'''
60	headers = headers or {}	×
61	headers.update({'Accept': 'application/json'})	×
62
63	if not xmlContent:	×
64	status, response = callServer('put', serverEndpoint, '/rmeta/text', string, headers, False, config_path=config_path, requestOptions=requestOptions)	×
65	else:
66	status, response = callServer('put', serverEndpoint, '/rmeta/xml', string, headers, False, config_path=config_path, requestOptions=requestOptions)	×
67
68	if raw_response:	×
69	return (status, response)	×
70	else:
71	return _parse((status,response))	×
72
73	def _parse(output, service='all'):	×
74	'''
75	Parses response from Tika REST API server
76	:param output: output from Tika Server
77	:param service: service requested from the tika server
78	Default is 'all', which results in recursive text content+metadata.
79	'meta' returns only metadata
80	'text' returns only content
81	:return: a dictionary having 'metadata' and 'content' values
82	'''
83	parsed={'metadata': None, 'content': None}	×
84	if not output:	×
85	return parsed	×
86
87	parsed["status"] = output[0]	×
88	if output[1] is None or output[1] == "":	×
89	return parsed	×
90
91	if service == "text":	×
92	parsed["content"] = output[1]	×
93	return parsed	×
94
95	realJson = json.loads(output[1])	×
96
97	parsed["metadata"] = {}	×
98	if service == "meta":	×
99	for key in realJson:	×
100	parsed["metadata"][key] = realJson[key]	×
101	return parsed	×
102
103	content = ""	×
104	for js in realJson:	×
105	if "X-TIKA:content" in js:	×
106	content += js["X-TIKA:content"]	×
107
108	if content == "":	×
109	content = None	×
110
111	parsed["content"] = content	×
112
113	for js in realJson:	×
114	for n in js:	×
115	if n != "X-TIKA:content":	×
116	if n in parsed["metadata"]:	×
117	if not isinstance(parsed["metadata"][n], list):	×
118	parsed["metadata"][n] = [parsed["metadata"][n]]	×
119	parsed["metadata"][n].append(js[n])	×
120	else:
121	parsed["metadata"][n] = js[n]	×
122
123	return parsed	×

chrismattmann / tika-python / 24964326097

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous