aboutsummaryrefslogtreecommitdiffstats
path: root/python/ia_pdf_match.py
blob: 8a95d952fb9e563adc8d191285bd43e145b17b77 (plain)
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
#!/usr/bin/env python3
"""
Input is IA item metadata JSON.
Ouput is insertable fatcat "match" JSON

- md5
- sha1
- sha256
- size
- urls
- cdx (list; empty here)

- dois (list)
- pmcid
- jstor
- arxiv

When invoking import matched, be sure to:

    --default-link-rel repository (?)
    --default-mimetype application/pdf
"""

import json
import sys
from typing import Any, Dict, Optional


def parse(obj: dict) -> Optional[Dict[str, Any]]:
    if obj["metadata"]["identifier"].endswith("-test") or obj["metadata"].get("test"):
        print("skip: test item", file=sys.stderr)
        return None

    extid_type = None
    extid = None
    if obj["metadata"]["identifier"].startswith("arxiv-"):
        extid_type = "arxiv"
        extid = obj["metadata"].get("source")
        if not extid:
            print("skip: no source", file=sys.stderr)
            return None
        assert extid.startswith("http://arxiv.org/abs/")
        extid = extid.replace("http://arxiv.org/abs/", "")
        # print(extid)
        assert "/" in extid or "." in extid
        if "v" not in extid or not extid[-1].isdigit():
            print("skip: non-versioned arxiv_id", file=sys.stderr)
            return None
    elif obj["metadata"]["identifier"].startswith("paper-doi-10_"):
        extid_type = "doi"
        extid = obj["metadata"]["identifier-doi"]
        assert extid.startswith("10.")
    elif obj["metadata"]["identifier"].startswith("pubmed-PMC"):
        extid_type = "pmcid"
        extid = obj["metadata"]["identifier"].replace("pubmed-", "")
        assert extid.startswith("PMC")
        int(extid[3:])
    elif obj["metadata"]["identifier"].startswith("jstor-"):
        extid_type = "jstor"
        extid = obj["metadata"]["identifier"].replace("jstor-", "")
        int(extid)
    else:
        raise NotImplementedError()

    pdf_file = None
    for f in obj["files"]:
        if f["source"] == "original" and "PDF" in f["format"]:
            pdf_file = f
            break
    if not pdf_file:
        print("skip: no PDF found: {}".format(obj["metadata"]["identifier"]), file=sys.stderr)
        # for f in obj['files']:
        #    print(f['format'], file=sys.stderr)
        return None

    assert pdf_file["name"].endswith(".pdf")

    match = {
        "md5": pdf_file["md5"],
        "sha1": pdf_file["sha1"],
        "size": int(pdf_file["size"]),
        "mimetype": "application/pdf",
        "urls": [
            "https://archive.org/download/{}/{}".format(
                obj["metadata"]["identifier"], pdf_file["name"]
            ),
        ],
        "cdx": [],
        "dois": [],
    }

    if extid_type == "doi":
        match["dois"] = [
            extid,
        ]
    else:
        match[extid_type] = extid

    return match


def run() -> None:
    for line in sys.stdin:
        if not line:
            continue
        obj = json.loads(line)
        match = parse(obj)
        if match is not None:
            print(json.dumps(match, sort_keys=True))


if __name__ == "__main__":
    run()