Loading scripts/demo.py 0 → 100644 +72 −0 Original line number Diff line number Diff line import shutil import tempfile import time from pathlib import Path from typer.testing import CliRunner from tdoc_crawler.cli import app from tdoc_crawler.cli.console import get_console this_dir = Path(__file__).parent # Example data TDOC1 = "S4-260001" # docx TDOC2 = "S4-260002" # xlsx TDOC3 = "S4-260003" # pptx TDOCS = [TDOC1, TDOC2, TDOC3] MEETING1 = "SA#123" MEETING2 = "SA#124" WORKING_GROUP1 = "RAN#1" WORKING_GROUP2 = "SA#4" DATE1 = "2024-01-01" DATE2 = "2024-02-01" def main() -> None: runner = CliRunner() console = get_console() tmp_dir_args = {"suffix": "tdoc", "dir": this_dir, "delete": True} # Set to False to inspect cache contents after run cache_dir = this_dir / "cache" # Default cache dir if not using temp dir shutil.rmtree(cache_dir, ignore_errors=True) # Clean up any existing cache dir before run # with tempfile.TemporaryDirectory(**tmp_dir_args) as cache_dir: common_args = ["--cache-dir", cache_dir, "-v", "debug"] # 1. Simply open documents (no metadata crawling) for tdoc in TDOCS: console.print(f"Testing with {tdoc}...") res = runner.invoke(app, ["open", tdoc] + common_args) console.print(res.output) # wait until documents are opened before testing checkout, to avoid potential race conditions time.sleep(5) # with tempfile.TemporaryDirectory(**tmp_dir_args) as cache_dir: # common_args = ["--cache-dir", cache_dir, "-v", "debug"] # 2. Test checkout command (no metadata crawling if not explicitly requested) res = runner.invoke(app, ["checkout"] + TDOCS + common_args) console.print(res.output) # 3. Crawl Meetings res = runner.invoke(app, ["crawl-meetings"] + TDOCS + common_args) console.print(res.output) # 4. Crawl TDocs # 5. Query TDocs # 6. Simply open spec documents (no metadata crawling) # 7. Checkout spec documents (no metadata crawling) # 8. Crawl spec metadata # 9. Query spec metadata if __name__ == "__main__": main() Loading
scripts/demo.py 0 → 100644 +72 −0 Original line number Diff line number Diff line import shutil import tempfile import time from pathlib import Path from typer.testing import CliRunner from tdoc_crawler.cli import app from tdoc_crawler.cli.console import get_console this_dir = Path(__file__).parent # Example data TDOC1 = "S4-260001" # docx TDOC2 = "S4-260002" # xlsx TDOC3 = "S4-260003" # pptx TDOCS = [TDOC1, TDOC2, TDOC3] MEETING1 = "SA#123" MEETING2 = "SA#124" WORKING_GROUP1 = "RAN#1" WORKING_GROUP2 = "SA#4" DATE1 = "2024-01-01" DATE2 = "2024-02-01" def main() -> None: runner = CliRunner() console = get_console() tmp_dir_args = {"suffix": "tdoc", "dir": this_dir, "delete": True} # Set to False to inspect cache contents after run cache_dir = this_dir / "cache" # Default cache dir if not using temp dir shutil.rmtree(cache_dir, ignore_errors=True) # Clean up any existing cache dir before run # with tempfile.TemporaryDirectory(**tmp_dir_args) as cache_dir: common_args = ["--cache-dir", cache_dir, "-v", "debug"] # 1. Simply open documents (no metadata crawling) for tdoc in TDOCS: console.print(f"Testing with {tdoc}...") res = runner.invoke(app, ["open", tdoc] + common_args) console.print(res.output) # wait until documents are opened before testing checkout, to avoid potential race conditions time.sleep(5) # with tempfile.TemporaryDirectory(**tmp_dir_args) as cache_dir: # common_args = ["--cache-dir", cache_dir, "-v", "debug"] # 2. Test checkout command (no metadata crawling if not explicitly requested) res = runner.invoke(app, ["checkout"] + TDOCS + common_args) console.print(res.output) # 3. Crawl Meetings res = runner.invoke(app, ["crawl-meetings"] + TDOCS + common_args) console.print(res.output) # 4. Crawl TDocs # 5. Query TDocs # 6. Simply open spec documents (no metadata crawling) # 7. Checkout spec documents (no metadata crawling) # 8. Crawl spec metadata # 9. Query spec metadata if __name__ == "__main__": main()