File: generate_registry

package info (click to toggle)
odil 0.12.0-2
  • links: PTS, VCS
  • area: main
  • in suites: bullseye, sid
  • size: 5,092 kB
  • sloc: cpp: 54,080; python: 3,896; xml: 182; makefile: 94
file content (180 lines) | stat: -rwxr-xr-x 5,587 bytes parent folder | download | duplicates (2)
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
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
#!/usr/bin/env python3

import argparse
import os
import re
import urllib.request
import sys
import xml.etree.ElementTree

import jinja2

def main():
    parser = argparse.ArgumentParser("Generate registry files")
    parser.add_argument(
        "root", nargs="?",
        default="http://dicom.nema.org/medical/dicom/current/source/docbook",
        help="Root URL or path to the Docbook version of the DICOM standard")

    arguments = parser.parse_args()

    jinja_environment = jinja2.Environment(
        loader=jinja2.FileSystemLoader(os.path.dirname(__file__)),
        trim_blocks=True)

    sources = [
        ("part07/part07.xml", "table_E.1-1"),
        ("part06/part06.xml", "table_7-1"),
        ("part06/part06.xml", "table_8-1"),
        ("part06/part06.xml", "table_6-1"),
    ]

    elements_dictionary = {}
    for url, id_ in sources:
        url = os.path.join(arguments.root, url)
        entries = parse_elements_dictionaries(url, id_)
        for group, group_entries in entries.items():
            elements_dictionary.setdefault(group, []).extend(group_entries)

    sources = [
        ("part06/part06.xml", "table_A-1"),
    ]

    uids = []
    for url, id_ in sources:
        uids.extend(parse_uids(os.path.join(arguments.root, url), id_))

    group_templates = {
        "src/odil/registry_{}.h": jinja_environment.get_template("registry_group.h.tmpl"),
        "src/odil/registry_{}.cpp": jinja_environment.get_template("registry_group.cpp.tmpl"),
    }

    for group, group_items in elements_dictionary.items():
        for path, template in group_templates.items():
            suffix = "{:04x}".format(group) if group != "misc" else group
            with open(path.format(suffix), "w") as fd:
                fd.write(template.render(
                    elements_dictionary=group_items, group=suffix))

    main_templates = {
        "src/odil/registry.h": jinja_environment.get_template("registry.h.tmpl"),
        "src/odil/registry.cpp": jinja_environment.get_template("registry.cpp.tmpl"),
    }
    groups = [
        "{:04x}".format(x) if x != "misc" else x for x in elements_dictionary.keys()]
    for path, template in main_templates.items():
        with open(path, "w") as fd:
            fd.write(template.render(uids=uids, groups=groups))

def parse_elements_dictionaries(url, id_):
    fd = urllib.request.urlopen(url)
    document = xml.etree.ElementTree.parse(fd)
    fd.close()

    namespaces = {
        "xml": "http://www.w3.org/XML/1998/namespace",
        "docbook": "http://docbook.org/ns/docbook"
    }

    table = document.find(".//*[@xml:id=\"{}\"]".format(id_), namespaces)

    entries = {}

    for row in table.iterfind("./docbook:tbody/docbook:tr", namespaces):
        entry = row.findall("./docbook:td/docbook:para", namespaces)

        tag, name, keyword, vr, vm = entry[:5]

        if tag.getchildren():
            tag = tag.find("./docbook:emphasis", namespaces)
        tag = tag.text

        converters = [
            (
                r"\(([0-9a-fA-F]{4}),([0-9a-fA-F]{4})\)",
                lambda x,y: (int(x, 16), int(y, 16))
            ),
            (
                r"\(([0-9a-fA-Fx]{4}),([0-9a-fA-Fx]{4})\)",
                lambda x,y: str(x+y)
            )
        ]
        for expression, converter in converters:
            match = re.match(expression, tag)
            if match:
                tag = converter(*match.groups())
                break

        keyword = get_value(keyword, "ascii", namespaces)
        if not keyword:
            continue

        name = get_value(name, "utf-8", namespaces)
        vr = get_value(vr, "ascii", namespaces)
        vm = get_value(vm, "ascii", namespaces)

        if isinstance(tag, tuple):
            group = tag[0]
        elif isinstance(tag, str):
            group = "misc"
        else:
            raise NotImplementedError("Unknown tag type: ".format(type(tag)))

        entries.setdefault(group, []).append((tag, name, keyword, vr, vm))

    return entries

def parse_uids(url, id_):
    fd = urllib.request.urlopen(url)
    document = xml.etree.ElementTree.parse(fd)
    fd.close()

    namespaces = {
        "xml": "http://www.w3.org/XML/1998/namespace",
        "docbook": "http://docbook.org/ns/docbook"
    }

    table = document.find(".//*[@xml:id=\"{}\"]".format(id_), namespaces)

    keywords_map = {
        "12leadECGWaveformStorage": "TwelveleadECGWaveformStorage",
    }

    entries = []

    for row in table.iterfind("./docbook:tbody/docbook:tr", namespaces):
        entry = row.findall("./docbook:td/docbook:para", namespaces)
        uid, name, type_ = entry[:3]

        uid = get_value(uid, "ascii", namespaces)
        name = get_value(name, "ascii", namespaces)
        type_ = get_value(type_, "ascii", namespaces)

        if name == "(Retired)":
            continue

        retired = name.endswith(" (Retired)")
        keyword = name.replace(" (Retired)", "")
        keyword = re.sub(":.*", "", keyword)
        keyword = re.sub("\W", " ", keyword).strip().replace(" ", "")
        if retired:
            keyword += "_Retired"

        keyword = keywords_map.get(keyword, keyword)

        entries.append((uid, name, keyword, type_))

    return entries


def get_value(element, encoding, namespaces):
    emphasis = element.find("./docbook:emphasis", namespaces)
    if emphasis is not None:
        element = emphasis

    element = element.text or ""
    element = element.replace(u"\u200b", "").replace(u"\u00b5", "u")
    return element

if __name__ == "__main__":
    sys.exit(main())