Christian Fraß commited on 2021-03-03 00:26:17
Zeige 17 geänderte Dateien mit 55 Einfügungen und 382 Löschungen.
... | ... |
@@ -1,17 +0,0 @@ |
1 |
-import sys |
|
2 |
-import json |
|
3 |
- |
|
4 |
-def main(): |
|
5 |
- content = sys.stdin.read() |
|
6 |
- try: |
|
7 |
- data = json.loads(content) |
|
8 |
- print(content) |
|
9 |
- # print("valid") |
|
10 |
- return 0 |
|
11 |
- except ValueError as error: |
|
12 |
- print("invalid") |
|
13 |
- print(error) |
|
14 |
- return -1 |
|
15 |
- |
|
16 |
-sys.exit(main()) |
|
17 |
- |
... | ... |
@@ -1,111 +0,0 @@ |
1 |
-import json as _json |
|
2 |
-import os as _os |
|
3 |
-import re as _re |
|
4 |
- |
|
5 |
- |
|
6 |
-def dokuwiki_to(data): |
|
7 |
- content = "" |
|
8 |
- content += (" * type: %s\n" % (data["type"])) |
|
9 |
- content += (" * description: %s\n" % ("?" if (data["description"] is None) else data["description"])) |
|
10 |
- content += (" * tags\n") |
|
11 |
- for tag in data["tags"]: |
|
12 |
- content += (" * %s\n" % (tag)) |
|
13 |
- content += (" * translations\n") |
|
14 |
- for (language , lemmata) in data["translations"].items(): |
|
15 |
- content += (" * %s\n" % (language)) |
|
16 |
- for lemma in lemmata: |
|
17 |
- content += (" * %s\n" % (lemma)) |
|
18 |
- return content |
|
19 |
- |
|
20 |
- |
|
21 |
-def dokuwiki_from(content): |
|
22 |
- data = {} |
|
23 |
- state = "type" |
|
24 |
- lines = content.split("\n") |
|
25 |
- for line in lines: |
|
26 |
- if (line != ""): |
|
27 |
- if (state == "type"): |
|
28 |
- result = _re.match("^ \\* type: (.*)$", line) |
|
29 |
- if (result is not None): |
|
30 |
- data["type"] = result.group(1) |
|
31 |
- state = "description" |
|
32 |
- else: |
|
33 |
- raise ValueError("type expected in line '%s' while being in state '%s'" % (line, state)) |
|
34 |
- elif (state == "description"): |
|
35 |
- result = _re.match("^ \\* description: (.*)$", line) |
|
36 |
- if (result is not None): |
|
37 |
- data["description"] = (None if (result.group(1) == "?") else result.group(1)) |
|
38 |
- state = "tags" |
|
39 |
- else: |
|
40 |
- raise ValueError("description expected in line '%s' while being in state '%s'" % (line, state)) |
|
41 |
- elif (state == "tags"): |
|
42 |
- result = _re.match("^ \\* tags$", line) |
|
43 |
- if (result is not None): |
|
44 |
- data["tags"] = [] |
|
45 |
- state = "tagentry" |
|
46 |
- else: |
|
47 |
- raise ValueError("tags expected in line '%s' while being in state '%s'" % (line, state)) |
|
48 |
- elif (state == "tagentry"): |
|
49 |
- result = _re.match("^ \\* (.*)$", line) |
|
50 |
- if (result is not None): |
|
51 |
- data["tags"].append(result.group(1)) |
|
52 |
- state = "tagentry" |
|
53 |
- else: |
|
54 |
- result = _re.match("^ \\* translations$", line) |
|
55 |
- if (result is not None): |
|
56 |
- data["translations"] = {} |
|
57 |
- state = "language" |
|
58 |
- else: |
|
59 |
- raise ValueError("tag or translations expected in line '%s' while being in state '%s'" % (line, state)) |
|
60 |
- elif (state == "language"): |
|
61 |
- result = _re.match("^ \\* (.*)$", line) |
|
62 |
- if (result is not None): |
|
63 |
- language = result.group(1) |
|
64 |
- data["translations"][language] = [] |
|
65 |
- state = "lemma" |
|
66 |
- else: |
|
67 |
- raise ValueError("language expected in line '%s' while being in state '%s'" % (line, state)) |
|
68 |
- elif (state == "lemma"): |
|
69 |
- result = _re.match("^ \\* (.*)$", line) |
|
70 |
- if (result is not None): |
|
71 |
- lemma = result.group(1) |
|
72 |
- data["translations"][language].append(lemma) |
|
73 |
- state = "lemma" |
|
74 |
- else: |
|
75 |
- result = _re.match("^ \\* (.*)$", line) |
|
76 |
- if (result is not None): |
|
77 |
- language = result.group(1) |
|
78 |
- data["translations"][language] = [] |
|
79 |
- state = "lemma" |
|
80 |
- else: |
|
81 |
- raise ValueError("language or lemma expected in line '%s' while being in state '%s'" % (line, state)) |
|
82 |
- else: |
|
83 |
- raise ValueError("unhandled state '%s'" % (state)) |
|
84 |
- return data |
|
85 |
- |
|
86 |
- |
|
87 |
-def json_to(data): |
|
88 |
- content = _json.dumps(data, indent = "\t", ensure_ascii = False, sort_keys = True) |
|
89 |
- return content |
|
90 |
- |
|
91 |
- |
|
92 |
-def json_from(content): |
|
93 |
- data = _json.loads(content) |
|
94 |
- return data |
|
95 |
- |
|
96 |
- |
|
97 |
-def filemap(folder_from, convert_from, folder_to, convert_to, namemapper): |
|
98 |
- for name_from in _os.listdir(folder_from): |
|
99 |
- path_from = _os.path.join(folder_from, name_from) |
|
100 |
- handle_from = open(path_from, "r") |
|
101 |
- content_from = handle_from.read() |
|
102 |
- handle_from.close() |
|
103 |
- data = convert_from(content_from) |
|
104 |
- name_to = namemapper(name_from) |
|
105 |
- path_to = _os.path.join(folder_to, name_to) |
|
106 |
- content_to = convert_to(data) |
|
107 |
- handle_to = open(path_to, "w") |
|
108 |
- handle_to.write(content_to) |
|
109 |
- handle_to.close() |
|
110 |
- |
|
111 |
- |
... | ... |
@@ -1,50 +0,0 @@ |
1 |
-#!/usr/bin/env python3 |
|
2 |
- |
|
3 |
-import sys as _sys |
|
4 |
-import os as _os |
|
5 |
-import sqlite3 as _sqlite3 |
|
6 |
-import json as _json |
|
7 |
- |
|
8 |
- |
|
9 |
-def main(args): |
|
10 |
- path = _os.path.join("queries", "convert.sql.tpl") |
|
11 |
- handle = open(path, "r") |
|
12 |
- querytemplate = handle.read() |
|
13 |
- handle.close() |
|
14 |
- arguments = {} |
|
15 |
- connection = _sqlite3.connect(_os.path.join("db", "words.sqlite")) |
|
16 |
- result = connection.cursor().execute(querytemplate, arguments).fetchall() |
|
17 |
- connection.close() |
|
18 |
- for index in range(len(result)): |
|
19 |
- line = result[index] |
|
20 |
- if True: |
|
21 |
- id_ = line[0] |
|
22 |
- if True: |
|
23 |
- type_ = line[1] |
|
24 |
- if True: |
|
25 |
- description = line[2] |
|
26 |
- if True: |
|
27 |
- tags = ([] if (line[3] is None) else line[3].split("|")) |
|
28 |
- if True: |
|
29 |
- translations = {} |
|
30 |
- pairs = list(map(lambda x: tuple(x.split(":", 2)), line[4].split("|"))) |
|
31 |
- for (language , lemma) in sorted(pairs, key = lambda pair: pair[0]): |
|
32 |
- if (language not in translations): |
|
33 |
- translations[language] = [] |
|
34 |
- translations[language].append(lemma) |
|
35 |
- obj = { |
|
36 |
- "type": type_, |
|
37 |
- "description": description, |
|
38 |
- "tags": tags, |
|
39 |
- "translations": translations, |
|
40 |
- } |
|
41 |
- name = ("concept_%u.json" % (id_)) |
|
42 |
- path = _os.path.join("concepts", name) |
|
43 |
- output = _json.dumps(obj, indent = "\t", ensure_ascii = False) |
|
44 |
- handle = open(path, "w") |
|
45 |
- handle.write(output) |
|
46 |
- handle.close() |
|
47 |
- |
|
48 |
- |
|
49 |
-main(_sys.argv[1:]) |
|
50 |
- |
... | ... |
@@ -1,33 +0,0 @@ |
1 |
-import sys |
|
2 |
-import json |
|
3 |
- |
|
4 |
-def stringify(x): |
|
5 |
- if (x is None): |
|
6 |
- return "null" |
|
7 |
- elif (type(x) == str): |
|
8 |
- return ("\"%s\"" % x) |
|
9 |
- elif (type(x) == list): |
|
10 |
- return ("[%s]" % (",".join(map(lambda y: stringify(y), x)))) |
|
11 |
- else: |
|
12 |
- return str(x) |
|
13 |
- |
|
14 |
-def main(): |
|
15 |
- languages = ["fs","en","af","nl","yi","de","da","nb","sv","nn","is","pg"] |
|
16 |
- data = json.loads(sys.stdin.read()) |
|
17 |
- sys.stdout.write("[\n") |
|
18 |
- first = True |
|
19 |
- for entry in data: |
|
20 |
- if (first): |
|
21 |
- first = False |
|
22 |
- else: |
|
23 |
- sys.stdout.write(",\n") |
|
24 |
- s = "" |
|
25 |
- s += "\t{\n" |
|
26 |
- s += "\t\t%s: %s, %s: %s, %s: %s,\n" % (stringify("type"), stringify(entry["type"]), stringify("description"), stringify(entry["description"]), stringify("tags"), stringify(entry["tags"])) |
|
27 |
- s += "\t\t%s: {%s}\n" % (stringify("translations"), ", ".join(map(lambda language: "%s: %s" % (stringify(language), stringify(entry["translations"][language])), languages))) |
|
28 |
- s += "\t}" |
|
29 |
- sys.stdout.write(s) |
|
30 |
- sys.stdout.write("\n]\n") |
|
31 |
- |
|
32 |
-main() |
|
33 |
- |
... | ... |
@@ -0,0 +1,47 @@ |
1 |
+## directories |
|
2 |
+dir_source := source |
|
3 |
+dir_build := build |
|
4 |
+dir_lib := lib |
|
5 |
+ |
|
6 |
+## commands |
|
7 |
+cmd_dir_make := mkdir --parents |
|
8 |
+cmd_copy := cp --recursive --update --verbose |
|
9 |
+cmd_tsc := tsc --lib es2015,dom --target es6 |
|
10 |
+cmd_remove := rm --force |
|
11 |
+cmd_link := ln --symbolic |
|
12 |
+ |
|
13 |
+ |
|
14 |
+all: ${dir_build}/sql ${dir_build}/manage |
|
15 |
+.PHONY: all |
|
16 |
+ |
|
17 |
+${dir_build}/sql: |
|
18 |
+ @ ${cmd_dir_make} ${dir_build}/sql |
|
19 |
+ @ ${cmd_copy} ${dir_source}/sql/* ${dir_build}/sql/ |
|
20 |
+.PHONY: ${dir_build}/sql |
|
21 |
+ |
|
22 |
+${dir_build}/manage: \ |
|
23 |
+ ${dir_source}/types.ts \ |
|
24 |
+ ${dir_source}/helpers/string.ts \ |
|
25 |
+ ${dir_source}/helpers/file.ts \ |
|
26 |
+ ${dir_source}/helpers/database.ts \ |
|
27 |
+ ${dir_source}/helpers/misc.ts \ |
|
28 |
+ ${dir_source}/helpers/module.ts \ |
|
29 |
+ ${dir_source}/helpers/storage.ts \ |
|
30 |
+ ${dir_source}/helpers/repository.ts \ |
|
31 |
+ ${dir_source}/entities/concept.ts \ |
|
32 |
+ ${dir_source}/repositories/language.ts \ |
|
33 |
+ ${dir_source}/repositories/type.ts \ |
|
34 |
+ ${dir_source}/repositories/tag.ts \ |
|
35 |
+ ${dir_source}/repositories/concept-core.ts \ |
|
36 |
+ ${dir_source}/repositories/concept-tags.ts \ |
|
37 |
+ ${dir_source}/repositories/concept-translations.ts \ |
|
38 |
+ ${dir_source}/repositories/concept.ts \ |
|
39 |
+ ${dir_source}/services/language.ts \ |
|
40 |
+ ${dir_source}/services/type.ts \ |
|
41 |
+ ${dir_source}/services/tag.ts \ |
|
42 |
+ ${dir_source}/services/concept.ts \ |
|
43 |
+ ${dir_source}/main.ts |
|
44 |
+ @ ${cmd_dir_make} ${dir_build} |
|
45 |
+ @ ${cmd_tsc} $^ --outFile $@ |
|
46 |
+ @ chmod +x ${dir_build}/manage |
|
47 |
+ |
... | ... |
@@ -1,21 +0,0 @@ |
1 |
-#!/usr/bin/env python3 |
|
2 |
- |
|
3 |
-import os as _os |
|
4 |
-import json as _json |
|
5 |
- |
|
6 |
- |
|
7 |
-def main(): |
|
8 |
- data = [] |
|
9 |
- folder = "concepts/json" |
|
10 |
- for name in sorted(_os.listdir(folder)): |
|
11 |
- path = _os.path.join(folder, name) |
|
12 |
- handle = open(path, "r") |
|
13 |
- content = handle.read() |
|
14 |
- handle.close() |
|
15 |
- entry = _json.loads(content) |
|
16 |
- data.append(entry) |
|
17 |
- print(_json.dumps(data)) |
|
18 |
- |
|
19 |
- |
|
20 |
-main() |
|
21 |
- |
... | ... |
@@ -1,17 +0,0 @@ |
1 |
-#!/usr/bin/env sh |
|
2 |
- |
|
3 |
-path=concepts.json |
|
4 |
-python3 tools/merge.py > ${path} |
|
5 |
- |
|
6 |
-destination=mehl:/home/bfadmin/websites/folksprak.org/htdocs/data |
|
7 |
-rsync \ |
|
8 |
- --verbose \ |
|
9 |
- --archive \ |
|
10 |
- --compress \ |
|
11 |
- --recursive \ |
|
12 |
- --rsh=ssh \ |
|
13 |
- ${path} \ |
|
14 |
- ${destination}/ |
|
15 |
- |
|
16 |
-rm ${path} |
|
17 |
- |
... | ... |
@@ -1,23 +0,0 @@ |
1 |
-import sys |
|
2 |
-import json |
|
3 |
- |
|
4 |
-def index(type_): |
|
5 |
- return { |
|
6 |
- "verb": 00, |
|
7 |
- "attribute": 10, |
|
8 |
- "noun": 20, |
|
9 |
- "pronoun": 30, |
|
10 |
- "correlative": 40, |
|
11 |
- "preposition": 50, |
|
12 |
- "article": 60, |
|
13 |
- "number": 70, |
|
14 |
- "other": 80, |
|
15 |
- }[type_] |
|
16 |
- |
|
17 |
-def main(): |
|
18 |
- data = json.loads(sys.stdin.read()) |
|
19 |
- data_ = sorted(data, key = lambda entry: index(entry["type"])) |
|
20 |
- print(json.dumps(data_, indent="\t")) |
|
21 |
- |
|
22 |
-main() |
|
23 |
- |
... | ... |
@@ -1,35 +0,0 @@ |
1 |
-import sys |
|
2 |
-import json |
|
3 |
- |
|
4 |
-def sqlformat(x): |
|
5 |
- if (x is None): |
|
6 |
- return "NULL" |
|
7 |
- elif (type(x) == str): |
|
8 |
- return ("'%s'" % x.replace("'", "\\'")) |
|
9 |
- else: |
|
10 |
- return str(x) |
|
11 |
- |
|
12 |
-def lastid(tablename): |
|
13 |
- return ("(SELECT id FROM %s ORDER BY id DESC LIMIT 1)" % (tablename)) |
|
14 |
- |
|
15 |
-def main(): |
|
16 |
- data = json.loads(sys.stdin.read()) |
|
17 |
- print(len(data)) |
|
18 |
- return |
|
19 |
- for entry in data[324:]: |
|
20 |
- query = "" |
|
21 |
- query += ("INSERT INTO\n\tconcepts(type,description)\nVALUES\n\t(%s,%s)\n;\n" % (sqlformat(entry["type"]), sqlformat(entry["description"]))) |
|
22 |
- concept_id = lastid("concepts") |
|
23 |
- for (iso_639_2,lemmata) in list(entry["translations"].items()): |
|
24 |
- for lemma in lemmata: |
|
25 |
- query += ("INSERT INTO\n\twords(language_id,lemma,pronunciation)\nVALUES\n\t((SELECT id FROM languages WHERE iso_639_2=%s),%s,%s)\n;\n" % (sqlformat(iso_639_2), sqlformat(lemma), sqlformat(None))) |
|
26 |
- word_id = lastid("words") |
|
27 |
- strength = None |
|
28 |
- query += ("INSERT INTO\n\tcorrelations(concept_id,word_id,strength)\nVALUES\n\t(%s,%s,%s)\n;\n" % (concept_id, word_id, sqlformat(strength))) |
|
29 |
- for tag in entry["tags"]: |
|
30 |
- query += ("INSERT INTO tags(concept_id,tag) VALUES (%s,%s);\n" % (concept_id, sqlformat(tag))) |
|
31 |
- query += "--\n" |
|
32 |
- sys.stdout.write(query) |
|
33 |
- |
|
34 |
-main() |
|
35 |
- |
... | ... |
@@ -1,19 +0,0 @@ |
1 |
-#!/usr/bin/env python3 |
|
2 |
- |
|
3 |
-import sys as _sys |
|
4 |
- |
|
5 |
-import common as _common |
|
6 |
- |
|
7 |
- |
|
8 |
-def main(args): |
|
9 |
- _common.filemap( |
|
10 |
- "concepts/json", |
|
11 |
- _common.json_from, |
|
12 |
- "concepts/wiki", |
|
13 |
- _common.dokuwiki_to, |
|
14 |
- lambda name_from: ("concept_%u.txt" % (int(name_from.split(".")[0].split("_")[1]))) |
|
15 |
- ) |
|
16 |
- |
|
17 |
- |
|
18 |
-main(_sys.argv[1:]) |
|
19 |
- |
... | ... |
@@ -1,14 +0,0 @@ |
1 |
-#!/usr/bin/env sh |
|
2 |
- |
|
3 |
-source=mehl:/home/bfadmin/websites/folksprak.org/htdocs/wiki/data/pages/concepts |
|
4 |
-destination=concepts/wiki |
|
5 |
-mkdir --parents ${destination} |
|
6 |
-rsync \ |
|
7 |
- --verbose \ |
|
8 |
- --archive \ |
|
9 |
- --compress \ |
|
10 |
- --recursive \ |
|
11 |
- --rsh=ssh \ |
|
12 |
- ${source}/* \ |
|
13 |
- ${destination}/ |
|
14 |
- |
... | ... |
@@ -1,13 +0,0 @@ |
1 |
-#!/usr/bin/env sh |
|
2 |
- |
|
3 |
-source=concepts/wiki |
|
4 |
-destination=mehl:/home/bfadmin/websites/folksprak.org/htdocs/wiki/data/pages/concepts |
|
5 |
-rsync \ |
|
6 |
- --verbose \ |
|
7 |
- --archive \ |
|
8 |
- --compress \ |
|
9 |
- --recursive \ |
|
10 |
- --rsh=ssh \ |
|
11 |
- ${source}/* \ |
|
12 |
- ${destination}/ |
|
13 |
- |
... | ... |
@@ -1,19 +0,0 @@ |
1 |
-#!/usr/bin/env python3 |
|
2 |
- |
|
3 |
-import sys as _sys |
|
4 |
- |
|
5 |
-import common as _common |
|
6 |
- |
|
7 |
- |
|
8 |
-def main(args): |
|
9 |
- _common.filemap( |
|
10 |
- "concepts/wiki", |
|
11 |
- _common.dokuwiki_from, |
|
12 |
- "concepts/json", |
|
13 |
- _common.json_to, |
|
14 |
- lambda name_from: ("concept_%u.json" % (int(name_from.split(".")[0].split("_")[1]))) |
|
15 |
- ) |
|
16 |
- |
|
17 |
- |
|
18 |
-main(_sys.argv[1:]) |
|
19 |
- |
|
20 | 0 |