1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
|
#!/usr/bin/env python3
"""
This is a helper script to convert ONIX XML (eg, from Scholar's Portal) to Onix CSV format.
Rough XML schema:
oph:HoldingsList
oph:HoldingsRecord (many)
oph:NotificationType text "00" (?)
oph:ResourceVersion
oph:ResourceVersionIdentifier
oph:ResourceVersionIDType "07" is ISSN?
oph:IDValue
oph:Title
oph:TitleText journal title
oph:Publisher
oph:PublisherName publisher name
oph:OnlinePackage
oph:PackageDetail (multiple)
oph:Coverage
oph:CoverageDescriptionLevel "03"
oph:FixedCoverage
oph:Release (multiple)
oph:Enumeration
oph:Level1
oph:Unit "Volume"
oph:Number volume number
oph:Level2
oph:Unit "Issue"
oph:Number issue number
oph:NominalDate
oph:DateFormat "01"
oph:Date partial date, eg "197803"
oph:PreservationStatus
oph:PreservationStatusCode "05"
oph:VerificationStatus "01"
ONIX CSV columns:
ISSN
Title
Publisher
Url
Vol
No
Published
Deposited
"""
import sys
import csv
import argparse
import xml.etree.ElementTree as ET
from typing import List, Any, Dict, AnyStr, Optional
oph = "{http://www.editeur.org/onix/serials/SOH}"
xml_ns = {
"oph": "http://www.editeur.org/onix/serials/SOH",
}
def fix_issn(raw: str) -> Optional[str]:
if len(raw) == 9:
return raw
if len(raw) == 8:
return f"{raw[:4]}-{raw[4:8]}"
return None
def fix_date(raw: str) -> str:
if len(raw) == 6 and raw.isdigit():
return f"{raw[:4]}-{raw[4:6]}"
return raw
def fix_str(raw: Optional[str]) -> Optional[str]:
if not raw:
return None
return raw.strip().replace('\n', ' ')
def resource_to_rows(resource) -> List[dict]:
rows = []
base = dict()
if resource.find('oph:ResourceVersionIdentifier/oph:ResourceVersionIDType', xml_ns).text != "07":
return []
base['ISSN'] = fix_issn(resource.find('oph:ResourceVersionIdentifier/oph:IDValue', xml_ns).text)
base['Title'] = fix_str(resource.find('oph:Title/oph:TitleText', xml_ns).text)
if not base['Title']:
return []
base['Publisher'] = fix_str(resource.find('oph:Publisher/oph:PublisherName', xml_ns).text)
base['Url'] = ''
base['Deposited'] = ''
for package in resource.findall('oph:OnlinePackage/oph:PackageDetail', xml_ns):
if package.find('oph:Coverage/oph:CoverageDescriptionLevel', xml_ns).text != "03":
continue
if package.find('oph:VerificationStatus', xml_ns).text != "01":
continue
if package.find('oph:PreservationStatus/oph:PreservationStatusCode', xml_ns).text != "05":
continue
for release in package.findall('oph:Coverage/oph:FixedCoverage/oph:Release', xml_ns):
row = dict()
if release.find('oph:Enumeration/oph:Level1/oph:Unit', xml_ns).text != "Volume":
continue
row['Vol'] = release.find('oph:Enumeration/oph:Level1/oph:Number', xml_ns).text
if release.find('oph:Enumeration/oph:Level2/oph:Unit', xml_ns).text != "Issue":
continue
row['No'] = release.find('oph:Enumeration/oph:Level2/oph:Number', xml_ns).text
if release.find('oph:NominalDate/oph:Date', xml_ns) == None:
continue
row['Published'] = fix_date(release.find('oph:NominalDate/oph:Date', xml_ns).text)
row.update(base)
rows.append(row)
return rows
def onix_xml_to_csv(xml_input_file, csv_output_file):
elem_iter = ET.iterparse(xml_input_file, ["start", "end"])
fieldnames = ['ISSN', 'Title', 'Publisher', 'Url', 'Vol', 'No', 'Published', 'Deposited']
writer = csv.DictWriter(csv_output_file, fieldnames=fieldnames)
writer.writeheader()
root = None
for (event, element) in elem_iter:
#print(element, file=sys.stderr)
if not root and event == "start":
root = element
continue
if not (element.tag == f"{oph}ResourceVersion" and event == "end"):
continue
for row in resource_to_rows(element):
writer.writerow(row)
element.clear()
root.clear()
def main() -> None: # pragma no cover
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description="ONIX XML to JSON",
usage="%(prog)s <xml_input_file> <csv_output_file>",
)
parser.add_argument("xml_input_file", type=argparse.FileType('r'))
parser.add_argument("csv_output_file", type=argparse.FileType('w'))
args = parser.parse_args()
onix_xml_to_csv(args.xml_input_file, args.csv_output_file)
if __name__ == "__main__": # pragma no cover
main()
|
