Compare commits
2 Commits
7591a71471
...
85315d9c1c
| Author | SHA1 | Date | |
|---|---|---|---|
| 85315d9c1c | |||
| 2de0faabdb |
128
chatmastermind/glossary.py
Normal file
128
chatmastermind/glossary.py
Normal file
@ -0,0 +1,128 @@
|
|||||||
|
"""
|
||||||
|
Module implementing glossaries for translations.
|
||||||
|
"""
|
||||||
|
import yaml
|
||||||
|
import tempfile
|
||||||
|
import shutil
|
||||||
|
import csv
|
||||||
|
from pathlib import Path
|
||||||
|
from dataclasses import dataclass, field
|
||||||
|
from typing import Type, TypeVar
|
||||||
|
|
||||||
|
GlossaryInst = TypeVar('GlossaryInst', bound='Glossary')
|
||||||
|
|
||||||
|
|
||||||
|
class GlossaryError(Exception):
|
||||||
|
pass
|
||||||
|
|
||||||
|
|
||||||
|
def str_presenter(dumper: yaml.Dumper, data: str) -> yaml.ScalarNode:
|
||||||
|
"""
|
||||||
|
Changes the YAML dump style to multiline syntax for multiline strings.
|
||||||
|
"""
|
||||||
|
if len(data.splitlines()) > 1:
|
||||||
|
return dumper.represent_scalar('tag:yaml.org,2002:str', data, style='|')
|
||||||
|
return dumper.represent_scalar('tag:yaml.org,2002:str', data)
|
||||||
|
|
||||||
|
|
||||||
|
@dataclass
|
||||||
|
class Glossary:
|
||||||
|
"""
|
||||||
|
A glossary consists of the following parameters:
|
||||||
|
- Name (freely selectable)
|
||||||
|
- Path (full file path)
|
||||||
|
- Source language
|
||||||
|
- Target language
|
||||||
|
- Entries (pairs of source lang and target lang terms)
|
||||||
|
- ID (automatically generated / modified, required by DeepL)
|
||||||
|
"""
|
||||||
|
|
||||||
|
name: str
|
||||||
|
source_lang: str
|
||||||
|
target_lang: str
|
||||||
|
entries: dict[str, str] = field(default_factory=lambda: dict())
|
||||||
|
file_path: Path | None = None
|
||||||
|
ID: str | None = None
|
||||||
|
|
||||||
|
@classmethod
|
||||||
|
def from_file(cls: Type[GlossaryInst], file_path: Path) -> GlossaryInst:
|
||||||
|
"""
|
||||||
|
Create a glossary from the given file.
|
||||||
|
"""
|
||||||
|
with open(file_path, "r") as fd:
|
||||||
|
try:
|
||||||
|
data = yaml.load(fd, Loader=yaml.FullLoader)
|
||||||
|
# remove any quotes from the entries that YAML may have added while dumping
|
||||||
|
# (e. g. for special keywords like 'yes')
|
||||||
|
clean_entries = {key.strip('\"\' '): value for key, value in data['Entries'].items()}
|
||||||
|
return cls(name=data['Name'],
|
||||||
|
source_lang=data['SourceLang'],
|
||||||
|
target_lang=data['TargetLang'],
|
||||||
|
entries=clean_entries,
|
||||||
|
file_path=file_path,
|
||||||
|
ID=data['ID'] if data['ID'] != 'None' else None)
|
||||||
|
except Exception:
|
||||||
|
raise GlossaryError(f"'{file_path}' does not contain a valid glossary")
|
||||||
|
|
||||||
|
def to_file(self, file_path: Path | None = None) -> None:
|
||||||
|
"""
|
||||||
|
Write glossary to given file.
|
||||||
|
"""
|
||||||
|
if file_path:
|
||||||
|
self.file_path = file_path
|
||||||
|
if not self.file_path:
|
||||||
|
raise GlossaryError("Got no valid path to write glossary")
|
||||||
|
# write YAML
|
||||||
|
with tempfile.NamedTemporaryFile(dir=self.file_path.parent, prefix=self.file_path.name, mode="w", delete=False) as temp_fd:
|
||||||
|
temp_file_path = Path(temp_fd.name)
|
||||||
|
data = {'Name': self.name,
|
||||||
|
'ID': str(self.ID),
|
||||||
|
'SourceLang': self.source_lang,
|
||||||
|
'TargetLang': self.target_lang,
|
||||||
|
'Entries': self.entries}
|
||||||
|
yaml.dump(data, temp_fd, sort_keys=False)
|
||||||
|
shutil.move(temp_file_path, self.file_path)
|
||||||
|
|
||||||
|
def export_csv(self, dictionary: dict[str, str], file_path: Path) -> None:
|
||||||
|
"""
|
||||||
|
Export the 'entries' of this glossary to a file in CSV format (compatible with DeepL).
|
||||||
|
"""
|
||||||
|
with open(file_path, 'w', newline='', encoding='utf-8') as csvfile:
|
||||||
|
writer = csv.writer(csvfile, delimiter=',', quotechar='"', quoting=csv.QUOTE_ALL)
|
||||||
|
for source_entry, target_entry in self.entries.items():
|
||||||
|
writer.writerow([source_entry, target_entry])
|
||||||
|
|
||||||
|
def export_tsv(self, entries: dict[str, str], file_path: Path) -> None:
|
||||||
|
"""
|
||||||
|
Export the 'entries' of this glossary to a file in TSV format (compatible with DeepL).
|
||||||
|
"""
|
||||||
|
with open(file_path, 'w', encoding='utf-8') as file:
|
||||||
|
for source_entry, target_entry in self.entries.items():
|
||||||
|
file.write(f"{source_entry}\t{target_entry}\n")
|
||||||
|
|
||||||
|
def import_csv(self, file_path: Path) -> None:
|
||||||
|
"""
|
||||||
|
Import the entries from the given CSV file to those of the current glossary.
|
||||||
|
Existing entries are overwritten.
|
||||||
|
"""
|
||||||
|
try:
|
||||||
|
with open(file_path, mode='r', encoding='utf-8') as csvfile:
|
||||||
|
reader = csv.reader(csvfile, delimiter=',', quotechar='"')
|
||||||
|
self.entries = {rows[0]: rows[1] for rows in reader if len(rows) >= 2}
|
||||||
|
except Exception as e:
|
||||||
|
raise GlossaryError(f"Error importing CSV: {e}")
|
||||||
|
|
||||||
|
def import_tsv(self, file_path: Path) -> None:
|
||||||
|
"""
|
||||||
|
Import the entries from the given CSV file to those of the current glossary.
|
||||||
|
Existing entries are overwritten.
|
||||||
|
"""
|
||||||
|
try:
|
||||||
|
with open(file_path, mode='r', encoding='utf-8') as tsvfile:
|
||||||
|
self.entries = {}
|
||||||
|
for line in tsvfile:
|
||||||
|
parts = line.strip().split('\t')
|
||||||
|
if len(parts) == 2:
|
||||||
|
self.entries[parts[0]] = parts[1]
|
||||||
|
except Exception as e:
|
||||||
|
raise GlossaryError(f"Error importing TSV: {e}")
|
||||||
92
tests/test_glossary.py
Normal file
92
tests/test_glossary.py
Normal file
@ -0,0 +1,92 @@
|
|||||||
|
import unittest
|
||||||
|
import tempfile
|
||||||
|
from pathlib import Path
|
||||||
|
from chatmastermind.glossary import Glossary
|
||||||
|
|
||||||
|
|
||||||
|
class TestGlossary(unittest.TestCase):
|
||||||
|
|
||||||
|
def test_from_file_valid_yaml(self) -> None:
|
||||||
|
# Prepare a temporary YAML file with valid content
|
||||||
|
with tempfile.NamedTemporaryFile('w', delete=False) as yaml_file:
|
||||||
|
yaml_file.write("Name: Sample\n"
|
||||||
|
"ID: '123'\n"
|
||||||
|
"SourceLang: en\n"
|
||||||
|
"TargetLang: es\n"
|
||||||
|
"Entries:\n"
|
||||||
|
" hello: hola\n"
|
||||||
|
" goodbye: adiós\n"
|
||||||
|
" 'yes': sí\n") # 'yes' is a YAML keyword and therefore quoted
|
||||||
|
yaml_file_path = Path(yaml_file.name)
|
||||||
|
|
||||||
|
glossary = Glossary.from_file(yaml_file_path)
|
||||||
|
self.assertEqual(glossary.name, "Sample")
|
||||||
|
self.assertEqual(glossary.source_lang, "en")
|
||||||
|
self.assertEqual(glossary.target_lang, "es")
|
||||||
|
self.assertEqual(glossary.entries, {"hello": "hola", "goodbye": "adiós", "yes": "sí"})
|
||||||
|
yaml_file_path.unlink() # Remove the temporary file
|
||||||
|
|
||||||
|
def test_to_file_writes_yaml(self) -> None:
|
||||||
|
# Create glossary instance
|
||||||
|
glossary = Glossary(name="Test", source_lang="en", target_lang="fr", entries={"yes": "oui"})
|
||||||
|
|
||||||
|
with tempfile.NamedTemporaryFile('w', delete=False) as tmp_file:
|
||||||
|
file_path = Path(tmp_file.name)
|
||||||
|
glossary.to_file(file_path)
|
||||||
|
|
||||||
|
with open(file_path, 'r') as file:
|
||||||
|
content = file.read()
|
||||||
|
|
||||||
|
self.assertIn("Name: Test", content)
|
||||||
|
self.assertIn("SourceLang: en", content)
|
||||||
|
self.assertIn("TargetLang: fr", content)
|
||||||
|
self.assertIn("Entries", content)
|
||||||
|
# 'yes' is a YAML keyword and therefore quoted
|
||||||
|
self.assertIn("'yes': oui", content)
|
||||||
|
file_path.unlink() # Remove the temporary file
|
||||||
|
|
||||||
|
def test_write_read_glossary(self) -> None:
|
||||||
|
# Create glossary instance
|
||||||
|
# -> use 'yes' in order to test if the YAML quoting is correctly removed when reading the file
|
||||||
|
glossary_write = Glossary(name="Test", source_lang="en", target_lang="fr", entries={"yes": "oui"})
|
||||||
|
|
||||||
|
with tempfile.NamedTemporaryFile('w', delete=False) as tmp_file:
|
||||||
|
file_path = Path(tmp_file.name)
|
||||||
|
glossary_write.to_file(file_path)
|
||||||
|
|
||||||
|
# create new instance from glossary file
|
||||||
|
glossary_read = Glossary.from_file(file_path)
|
||||||
|
self.assertEqual(glossary_write.name, glossary_read.name)
|
||||||
|
self.assertEqual(glossary_write.source_lang, glossary_read.source_lang)
|
||||||
|
self.assertEqual(glossary_write.target_lang, glossary_read.target_lang)
|
||||||
|
self.assertDictEqual(glossary_write.entries, glossary_read.entries)
|
||||||
|
|
||||||
|
file_path.unlink() # Remove the temporary file
|
||||||
|
|
||||||
|
def test_import_export_csv(self) -> None:
|
||||||
|
glossary = Glossary(name="Test", source_lang="en", target_lang="fr", entries={})
|
||||||
|
|
||||||
|
# First export to CSV
|
||||||
|
with tempfile.NamedTemporaryFile('w', delete=False) as csvfile:
|
||||||
|
csv_file_path = Path(csvfile.name)
|
||||||
|
glossary.entries = {"hello": "salut", "goodbye": "au revoir"}
|
||||||
|
glossary.export_csv(glossary.entries, csv_file_path)
|
||||||
|
|
||||||
|
# Now import CSV
|
||||||
|
glossary.import_csv(csv_file_path)
|
||||||
|
self.assertEqual(glossary.entries, {"hello": "salut", "goodbye": "au revoir"})
|
||||||
|
csv_file_path.unlink() # Remove the temporary file
|
||||||
|
|
||||||
|
def test_import_export_tsv(self) -> None:
|
||||||
|
glossary = Glossary(name="Test", source_lang="en", target_lang="fr", entries={})
|
||||||
|
|
||||||
|
# First export to TSV
|
||||||
|
with tempfile.NamedTemporaryFile('w', delete=False) as tsvfile:
|
||||||
|
tsv_file_path = Path(tsvfile.name)
|
||||||
|
glossary.entries = {"hello": "salut", "goodbye": "au revoir"}
|
||||||
|
glossary.export_tsv(glossary.entries, tsv_file_path)
|
||||||
|
|
||||||
|
# Now import TSV
|
||||||
|
glossary.import_tsv(tsv_file_path)
|
||||||
|
self.assertEqual(glossary.entries, {"hello": "salut", "goodbye": "au revoir"})
|
||||||
|
tsv_file_path.unlink() # Remove the temporary file
|
||||||
Loading…
x
Reference in New Issue
Block a user