@@ -194,10 +194,16 @@ def _processing_config(cfg: RunConfig, *, parquet_dir: Path, geom_wkt: str | Non
194194
195195
196196def _download_all (
197- urls : list [str ], mode : str , max_workers : int , cookie : str | None , cache_dir : Path , label : str
197+ urls : list [str ],
198+ mode : str ,
199+ max_workers : int ,
200+ cookie : str | None ,
201+ cache_dir : Path ,
202+ label : str ,
203+ description : str = "downloading" ,
198204) -> None :
199205 with (
200- progress_bar (len (urls ), unit = label ) as advance ,
206+ progress_bar (len (urls ), unit = label , description = description ) as advance ,
201207 concurrent .futures .ThreadPoolExecutor (max_workers = max_workers ) as pool ,
202208 ):
203209 for _ in pool .map (lambda u : download_osm_file (u , mode = mode , cookie = cookie , cache_dir = cache_dir ), urls ):
@@ -214,9 +220,10 @@ def _process_all(
214220 label : str ,
215221 workers : int ,
216222 extra_iterables : tuple [list , ...] = (),
223+ description : str = "processing" ,
217224) -> None :
218225 with (
219- progress_bar (len (items ), unit = label ) as advance ,
226+ progress_bar (len (items ), unit = label , description = description ) as advance ,
220227 concurrent .futures .ProcessPoolExecutor (
221228 max_workers = workers , initializer = initializer , initargs = init_args
222229 ) as pool ,
@@ -314,7 +321,9 @@ def run(cfg: RunConfig) -> dict[str, Any]:
314321 cs_config ["window_start_utc" ] = cfg .start_date .astimezone (UTC )
315322 cs_config ["window_end_utc" ] = cfg .end_date .astimezone (UTC )
316323
317- _download_all (urls , "changeset" , max_workers , None , cfg .cache_dir , "changesets" )
324+ _download_all (
325+ urls , "changeset" , max_workers , None , cfg .cache_dir , "changesets" , description = "Downloading changesets"
326+ )
318327 _process_all (
319328 urls ,
320329 target = process_changeset ,
@@ -323,6 +332,7 @@ def run(cfg: RunConfig) -> dict[str, Any]:
323332 chunksize = 10 ,
324333 label = "changesets" ,
325334 workers = max_workers ,
335+ description = "Processing changesets" ,
326336 )
327337 dbmod .merge_parquet_files (conn , cs_dir , cleanup = True )
328338 info ("Changeset processing complete." )
@@ -353,7 +363,15 @@ def run(cfg: RunConfig) -> dict[str, Any]:
353363 cf_config ["start_date_utc" ] = url_start_date_utc
354364 cf_config ["end_date_utc" ] = url_end_date_utc
355365
356- _download_all (urls , "changefiles" , max_workers , cookie , cfg .cache_dir , "changefiles" )
366+ _download_all (
367+ urls ,
368+ "changefiles" ,
369+ max_workers ,
370+ cookie ,
371+ cfg .cache_dir ,
372+ "changefiles" ,
373+ description = "Downloading changefiles" ,
374+ )
357375 chunksize = 10 if "minute" in url .lower () else 1
358376 seq_ids = list (range (src_start_seq , src_end_seq + 1 ))
359377 _process_all (
@@ -365,6 +383,7 @@ def run(cfg: RunConfig) -> dict[str, Any]:
365383 label = "changefiles" ,
366384 workers = max_workers ,
367385 extra_iterables = (seq_ids ,),
386+ description = "Processing changefiles" ,
368387 )
369388 dbmod .merge_parquet_files (conn , cf_dir , cleanup = True )
370389 upsert_state (
@@ -374,7 +393,7 @@ def run(cfg: RunConfig) -> dict[str, Any]:
374393 last_ts = url_end_date ,
375394 updated_at = dt .datetime .now (UTC ),
376395 )
377- info (f"Done : { url } " )
396+ info (f"Changefile processing complete : { url } " )
378397
379398 if cfg .delete_temp :
380399 # Never rmtree cfg.cache_dir itself — it may be the user's platform cache root.
0 commit comments