23369153415

Committed 21 Mar 2026 01:32AM UTC coverage: 77.306% (+2.5%) from 74.85%

Build # 23369153415

Build Type

push

github

Committed by

web-flow

Commit Message

Merge pull request #199 from IIIF/refactor-2026

Refactoring and using uv

Coverage Stats

467 of 564 new or added lines in 11 files covered. (82.8%)

4 existing lines in 1 file now uncovered.

729 of 943 relevant lines covered (77.31%)

3.09 hits per line

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

83.33

/presentation_validator/validator.py

from iiif_prezi.loader import ManifestReader
from jsonschema.exceptions import ValidationError
from presentation_validator.model import ValidationResult, ErrorDetail
from presentation_validator.v3 import schemavalidator
from presentation_validator.enum import IIIFVersion

import requests
from urllib.parse import urlparse
import traceback
from typing import Any

import json

from pyld import jsonld
jsonld.set_document_loader(jsonld.requests_document_loader(timeout=60))

IIIF_HEADER = "application/ld+json;profile=http://iiif.io/api/presentation/{version}/context.json"

def check_manifest(
                data,
                version: IIIFVersion,
                url: str | None = None,
                warnings: list[str] | None = None,
            ) -> dict[str, Any]:
    """Check manifest data at version, return JSON."""
    if warnings is None:
        warnings = []

    if isinstance(data, str):
        try:
            manifest = json.loads(data)
        except json.JSONDecodeError as e:
            result = ValidationResult()
            result.passed = False
            result.error = str(e)
            return result
    else:
        manifest = data

    result = ValidationResult()

    if not version:
        # peak into the json to find the version
        version = IIIFVersion.from_context(manifest.get('@context', ''))
        
    # Check if 3.0 if so run through schema rather than this version...
    if version == IIIFVersion.V3_0:
        try:
            result = schemavalidator.validate(manifest, version, url)
        
            # Only test ID match if working with remote URLs
            if url and url.startswith('http') and 'id' in manifest and manifest['id'] != url:
                raise ValidationError(f"The manifest id ({manifest['id']}) should be the same as the URL it is published at ({url}).")
        except ValidationError as e:
            if result.errorList:
                result.errorList.append(ErrorDetail(
                    'Resolve Error',
                    str(e),
                    '',
                    '/id',
                    '{ \'id\': \'...\'}',
                    e))
            else:
                result.passed = False
                result.error = str(e)
        except Exception as e:    
            traceback.print_exc()
            result.passed = False
            result.error = f'Presentation Validator bug: "{e}". Please create a <a href="https://github.com/IIIF/presentation-validator/issues">Validator Issue</a>, including a link to the manifest.'
    else:
        if isinstance(data, dict):
            data = json.dumps(data, indent=3)

        reader = ManifestReader(data, version=version)
        err = None
        try:
            mf = reader.read()
            mf.toJSON()
            if url and mf.id != url:
                raise ValidationError("Manifest @id ({}) is different to the location where it was retrieved ({})".format(mf.id, url))
            # Passed!
            result.passed = True
        except KeyError as e:    
            print ('Failed validation due to:')
            traceback.print_exc()
            err = 'Failed due to KeyError {}, check trace for details'.format(e)
            result.passed = False
        except Exception as e:
            # Failed
            print ('Failed validation due to:')
            traceback.print_exc()
            result.passed = False
            err = e

        warnings.extend(reader.get_warnings())

        result.warnings = warnings
        result.error = str(err)
        result.url = url

    return result

def fetch_manifest(url, accept, version):
    """
    Fetch a manifest from a URL.

    Args:
        url: URL to retrieve.
        accept: Whether to send an Accept header requesting a IIIF media type.
        version: Requested IIIF Presentation version, used to build the Accept header.
    """
    accept_header = None
    if accept and version:
        if version in ("2.0", "2.1"):
            accept_header = IIIF_HEADER.format(version=2)
        elif version in ("3.0",):
            accept_header = IIIF_HEADER.format(version=3)
        else:
            accept_header = "application/json"

    parsed_url = urlparse(url)
    if (parsed_url.scheme != 'http' and parsed_url.scheme != 'https'):
        raise ValueError("URLs must use HTTP or HTTPS")

    headers = {
        "User-Agent": "IIIF Validation Service",
        "Accept-Encoding": "gzip",
    }

    if accept_header:
        headers["Accept"] = accept_header

    response = requests.get(url, headers=headers)
    response.raise_for_status()

    warnings = []

    ct = response.headers.get("content-type", "")
    cors = response.headers.get("access-control-allow-origin", "")

    if not ct.startswith("application/json") and not ct.startswith("application/ld+json"):
        warnings.append(
            'URL does not have correct content-type header: got "%s", expected JSON' % ct
        )

    if cors != "*":
        warnings.append(
            'URL does not have correct access-control-allow-origin header: got "%s", expected *'
            % cors
        )

    content_encoding = response.headers.get("Content-Encoding", "")
    if content_encoding != "gzip":
        warnings.append(
            "The remote server did not use the requested gzip transfer compression, "
            "which will slow access. (Content-Encoding: %s)" % content_encoding
        )
    elif "Accept-Encoding" not in response.headers.get("Vary", ""):
        warnings.append(
            "gzip transfer compression is enabled but the Vary header does not include "
            "Accept-Encoding, which can cause compatibility issues"
        )

    return response.json(), warnings

1	from iiif_prezi.loader import ManifestReader	4✔
2	from jsonschema.exceptions import ValidationError	4✔
3	from presentation_validator.model import ValidationResult, ErrorDetail	4✔
4	from presentation_validator.v3 import schemavalidator	4✔
5	from presentation_validator.enum import IIIFVersion	4✔
6
7	import requests	4✔
8	from urllib.parse import urlparse	4✔
9	import traceback	4✔
10	from typing import Any	4✔
11
12	import json	4✔
13
14	from pyld import jsonld	4✔
15	jsonld.set_document_loader(jsonld.requests_document_loader(timeout=60))	4✔
16
17	IIIF_HEADER = "application/ld+json;profile=http://iiif.io/api/presentation/{version}/context.json"	4✔
18
19	def check_manifest(	4✔
20	data,
21	version: IIIFVersion,
22	url: str \| None = None,
23	warnings: list[str] \| None = None,
24	) -> dict[str, Any]:
25	"""Check manifest data at version, return JSON."""
26	if warnings is None:	4✔
27	warnings = []	4✔
28
29	if isinstance(data, str):	4✔
30	try:	4✔
31	manifest = json.loads(data)	4✔
32	except json.JSONDecodeError as e:	4✔
33	result = ValidationResult()	4✔
34	result.passed = False	4✔
35	result.error = str(e)	4✔
36	return result	4✔
37	else:
38	manifest = data	4✔
39
40	result = ValidationResult()	4✔
41
42	if not version:	4✔
43	# peak into the json to find the version
44	version = IIIFVersion.from_context(manifest.get('@context', ''))	4✔
45
46	# Check if 3.0 if so run through schema rather than this version...
47	if version == IIIFVersion.V3_0:	4✔
48	try:	4✔
49	result = schemavalidator.validate(manifest, version, url)	4✔
50
51	# Only test ID match if working with remote URLs
52	if url and url.startswith('http') and 'id' in manifest and manifest['id'] != url:	4✔
53	raise ValidationError(f"The manifest id ({manifest['id']}) should be the same as the URL it is published at ({url}).")	4✔
54	except ValidationError as e:	4✔
55	if result.errorList:	4✔
56	result.errorList.append(ErrorDetail(	4✔
57	'Resolve Error',
58	str(e),
59	'',
60	'/id',
61	'{ \'id\': \'...\'}',
62	e))
63	else:
NEW 64	result.passed = False	×
NEW 65	result.error = str(e)	×
NEW 66	except Exception as e:	×
NEW 67	traceback.print_exc()	×
NEW 68	result.passed = False	×
NEW 69	result.error = f'Presentation Validator bug: "{e}". Please create a <a href="https://github.com/IIIF/presentation-validator/issues">Validator Issue</a>, including a link to the manifest.'	×
70	else:
71	if isinstance(data, dict):	4✔
72	data = json.dumps(data, indent=3)	4✔
73
74	reader = ManifestReader(data, version=version)	4✔
75	err = None	4✔
76	try:	4✔
77	mf = reader.read()	4✔
78	mf.toJSON()	4✔
79	if url and mf.id != url:	4✔
NEW 80	raise ValidationError("Manifest @id ({}) is different to the location where it was retrieved ({})".format(mf.id, url))	×
81	# Passed!
82	result.passed = True	4✔
83	except KeyError as e:	4✔
NEW 84	print ('Failed validation due to:')	×
NEW 85	traceback.print_exc()	×
NEW 86	err = 'Failed due to KeyError {}, check trace for details'.format(e)	×
NEW 87	result.passed = False	×
88	except Exception as e:	4✔
89	# Failed
90	print ('Failed validation due to:')	4✔
91	traceback.print_exc()	4✔
92	result.passed = False	4✔
93	err = e	4✔
94
95	warnings.extend(reader.get_warnings())	4✔
96
97	result.warnings = warnings	4✔
98	result.error = str(err)	4✔
99	result.url = url	4✔
100
101	return result	4✔
102
103	def fetch_manifest(url, accept, version):	4✔
104	"""
105	Fetch a manifest from a URL.
106
107	Args:
108	url: URL to retrieve.
109	accept: Whether to send an Accept header requesting a IIIF media type.
110	version: Requested IIIF Presentation version, used to build the Accept header.
111	"""
112	accept_header = None	4✔
113	if accept and version:	4✔
114	if version in ("2.0", "2.1"):	4✔
NEW 115	accept_header = IIIF_HEADER.format(version=2)	×
116	elif version in ("3.0",):	4✔
117	accept_header = IIIF_HEADER.format(version=3)	4✔
118	else:
NEW 119	accept_header = "application/json"	×
120
121	parsed_url = urlparse(url)	4✔
122	if (parsed_url.scheme != 'http' and parsed_url.scheme != 'https'):	4✔
123	raise ValueError("URLs must use HTTP or HTTPS")	4✔
124
125	headers = {	4✔
126	"User-Agent": "IIIF Validation Service",
127	"Accept-Encoding": "gzip",
128	}
129
130	if accept_header:	4✔
131	headers["Accept"] = accept_header	4✔
132
133	response = requests.get(url, headers=headers)	4✔
134	response.raise_for_status()	4✔
135
136	warnings = []	4✔
137
138	ct = response.headers.get("content-type", "")	4✔
139	cors = response.headers.get("access-control-allow-origin", "")	4✔
140
141	if not ct.startswith("application/json") and not ct.startswith("application/ld+json"):	4✔
NEW 142	warnings.append(	×
143	'URL does not have correct content-type header: got "%s", expected JSON' % ct
144	)
145
146	if cors != "*":	4✔
NEW 147	warnings.append(	×
148	'URL does not have correct access-control-allow-origin header: got "%s", expected *'
149	% cors
150	)
151
152	content_encoding = response.headers.get("Content-Encoding", "")	4✔
153	if content_encoding != "gzip":	4✔
154	warnings.append(	4✔
155	"The remote server did not use the requested gzip transfer compression, "
156	"which will slow access. (Content-Encoding: %s)" % content_encoding
157	)
158	elif "Accept-Encoding" not in response.headers.get("Vary", ""):	4✔
NEW 159	warnings.append(	×
160	"gzip transfer compression is enabled but the Vary header does not include "
161	"Accept-Encoding, which can cause compatibility issues"
162	)
163
164	return response.json(), warnings	4✔

IIIF / presentation-validator / 23369153415

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