diff options
| author | Terry Truong <terry06890@gmail.com> | 2022-09-11 14:55:42 +1000 |
|---|---|---|
| committer | Terry Truong <terry06890@gmail.com> | 2022-09-11 15:04:14 +1000 |
| commit | 5de5fb93e50fe9006221b30ac4a66f1be0db82e7 (patch) | |
| tree | 2567c25c902dbb40d44419805cebb38171df47fa /backend/tolData/dbpedia/genDescData.py | |
| parent | daccbbd9c73a5292ea9d6746560d7009e5aa666d (diff) | |
Add backend unit tests
- Add unit testing code in backend/tests/
- Change to snake-case for script/file/directory names
- Use os.path.join() instead of '/'
- Refactor script code into function defs and a main-guard
- Make global vars all-caps
Some fixes:
- For getting descriptions, some wiki redirects weren't properly resolved
- Linked images were sub-optimally propagated
- Generation of reduced trees assumed a wiki-id association implied a description
- Tilo.py had potential null dereferences by not always using a reduced node set
- EOL image downloading didn't properly wait for all threads to end when finishing
Diffstat (limited to 'backend/tolData/dbpedia/genDescData.py')
| -rwxr-xr-x | backend/tolData/dbpedia/genDescData.py | 128 |
1 files changed, 0 insertions, 128 deletions
diff --git a/backend/tolData/dbpedia/genDescData.py b/backend/tolData/dbpedia/genDescData.py deleted file mode 100755 index 43ed815..0000000 --- a/backend/tolData/dbpedia/genDescData.py +++ /dev/null @@ -1,128 +0,0 @@ -#!/usr/bin/python3 - -import re -import bz2, sqlite3 - -import argparse -parser = argparse.ArgumentParser(description=""" -Adds DBpedia labels/types/abstracts/etc data into a database -""", formatter_class=argparse.RawDescriptionHelpFormatter) -parser.parse_args() - -labelsFile = 'labels_lang=en.ttl.bz2' # Had about 16e6 entries -idsFile = 'page_lang=en_ids.ttl.bz2' -redirectsFile = 'redirects_lang=en_transitive.ttl.bz2' -disambigFile = 'disambiguations_lang=en.ttl.bz2' -typesFile = 'instance-types_lang=en_specific.ttl.bz2' -abstractsFile = 'short-abstracts_lang=en.ttl.bz2' -dbFile = 'descData.db' -# In testing, this script took a few hours to run, and generated about 10GB - -print('Creating database') -dbCon = sqlite3.connect(dbFile) -dbCur = dbCon.cursor() - -print('Reading/storing label data') -dbCur.execute('CREATE TABLE labels (iri TEXT PRIMARY KEY, label TEXT)') -dbCur.execute('CREATE INDEX labels_idx ON labels(label)') -dbCur.execute('CREATE INDEX labels_idx_nc ON labels(label COLLATE NOCASE)') -labelLineRegex = re.compile(r'<([^>]+)> <[^>]+> "((?:[^"]|\\")+)"@en \.\n') -lineNum = 0 -with bz2.open(labelsFile, mode='rt') as file: - for line in file: - lineNum += 1 - if lineNum % 1e5 == 0: - print(f'At line {lineNum}') - # - match = labelLineRegex.fullmatch(line) - if match is None: - raise Exception(f'ERROR: Line {lineNum} has unexpected format') - dbCur.execute('INSERT INTO labels VALUES (?, ?)', (match.group(1), match.group(2))) - -print('Reading/storing wiki page ids') -dbCur.execute('CREATE TABLE ids (iri TEXT PRIMARY KEY, id INT)') -dbCur.execute('CREATE INDEX ids_idx ON ids(id)') -idLineRegex = re.compile(r'<([^>]+)> <[^>]+> "(\d+)".*\n') -lineNum = 0 -with bz2.open(idsFile, mode='rt') as file: - for line in file: - lineNum += 1 - if lineNum % 1e5 == 0: - print(f'At line {lineNum}') - # - match = idLineRegex.fullmatch(line) - if match is None: - raise Exception(f'ERROR: Line {lineNum} has unexpected format') - try: - dbCur.execute('INSERT INTO ids VALUES (?, ?)', (match.group(1), int(match.group(2)))) - except sqlite3.IntegrityError as e: - # Accounts for certain lines that have the same IRI - print(f'WARNING: Failed to add entry with IRI "{match.group(1)}": {e}') - -print('Reading/storing redirection data') -dbCur.execute('CREATE TABLE redirects (iri TEXT PRIMARY KEY, target TEXT)') -redirLineRegex = re.compile(r'<([^>]+)> <[^>]+> <([^>]+)> \.\n') -lineNum = 0 -with bz2.open(redirectsFile, mode='rt') as file: - for line in file: - lineNum += 1 - if lineNum % 1e5 == 0: - print(f'At line {lineNum}') - # - match = redirLineRegex.fullmatch(line) - if match is None: - raise Exception(f'ERROR: Line {lineNum} has unexpected format') - dbCur.execute('INSERT INTO redirects VALUES (?, ?)', (match.group(1), match.group(2))) - -print('Reading/storing diambiguation-page data') -dbCur.execute('CREATE TABLE disambiguations (iri TEXT PRIMARY KEY)') -disambigLineRegex = redirLineRegex -lineNum = 0 -with bz2.open(disambigFile, mode='rt') as file: - for line in file: - lineNum += 1 - if lineNum % 1e5 == 0: - print(f'At line {lineNum}') - # - match = disambigLineRegex.fullmatch(line) - if match is None: - raise Exception(f'ERROR: Line {lineNum} has unexpected format') - dbCur.execute('INSERT OR IGNORE INTO disambiguations VALUES (?)', (match.group(1),)) - -print('Reading/storing instance-type data') -dbCur.execute('CREATE TABLE types (iri TEXT, type TEXT)') -dbCur.execute('CREATE INDEX types_iri_idx ON types(iri)') -typeLineRegex = redirLineRegex -lineNum = 0 -with bz2.open(typesFile, mode='rt') as file: - for line in file: - lineNum += 1 - if lineNum % 1e5 == 0: - print(f'At line {lineNum}') - # - match = typeLineRegex.fullmatch(line) - if match is None: - raise Exception(f'ERROR: Line {lineNum} has unexpected format') - dbCur.execute('INSERT INTO types VALUES (?, ?)', (match.group(1), match.group(2))) - -print('Reading/storing abstracts') -dbCur.execute('CREATE TABLE abstracts (iri TEXT PRIMARY KEY, abstract TEXT)') -descLineRegex = labelLineRegex -lineNum = 0 -with bz2.open(abstractsFile, mode='rt') as file: - for line in file: - lineNum += 1 - if lineNum % 1e5 == 0: - print(f'At line {lineNum}') - # - if line[0] == '#': - continue - match = descLineRegex.fullmatch(line) - if match is None: - raise Exception(f'ERROR: Line {lineNum} has unexpected format') - dbCur.execute('INSERT INTO abstracts VALUES (?, ?)', - (match.group(1), match.group(2).replace(r'\"', '"'))) - -print('Closing database') -dbCon.commit() -dbCon.close() |
