XjdZddlZddlZddlmZddlmZddlmZddl m Z ddl m Z m Z dd lmZmZd d lmZmZd d lmZd d lmZejeZe dZgdZedGddZedGddZedGddZedGddZ edGddZ!edGddZ"d+de#ezdzde"fd Z$dede%e!fd!Z&d"edefd#Z'd$e(de#fd%Z)d&e*ee(fdedzde(fd'Z+d(ed)e#ddfd*Z,dS),z4Contains utilities to manage the HF cache directory.N) defaultdict) dataclass)Path)Literal) CacheNotFoundCorruptedCacheException) HF_HUB_CACHEREPO_TYPES_MAPPING) _shared_blobslogging)format_timesince)tabulate)modeldatasetspacekernel)z .DS_Storez Thumbs.dbz desktop.iniT)frozenceZdZUdZeed<eed<eed<eed<eed<eed<e defd Z e defd Z e defd Z d S) CachedFileInfoaCFrozen data structure holding information about a single cached file. Args: file_name (`str`): Name of the file. Example: `config.json`. file_path (`Path`): Path of the file in the `snapshots` directory. The file path is a symlink referring to a blob in the `blobs` folder. blob_path (`Path`): Path of the repo-local blob entry referenced by `file_path`. The blob entry can itself be a symlink to the cache-wide shared blob store. size_on_disk (`int`): Size of the blob file in bytes. blob_last_accessed (`float`): Timestamp of the last time the blob file has been accessed (from any revision). blob_last_modified (`float`): Timestamp of the last time the blob file has been modified/created. > [!WARNING] > `blob_last_accessed` and `blob_last_modified` reliability can depend on the OS you > are using. See [python documentation](https://docs.python.org/3/library/os.html#os.stat_result) > for more details. file_name file_path blob_path size_on_diskblob_last_accessedblob_last_modifiedreturnc*t|jS)z (property) Timestamp of the last time the blob file has been accessed (from any revision), returned as a human-readable string. Example: "2 weeks ago". )rrselfs UC:\Projects\Historical\venv\Lib\site-packages\huggingface_hub/utils/_cache_manager.pyblob_last_accessed_strz%CachedFileInfo.blob_last_accessed_strJ  7888c*t|jS)z (property) Timestamp of the last time the blob file has been modified, returned as a human-readable string. Example: "2 weeks ago". )rrr s r"blob_last_modified_strz%CachedFileInfo.blob_last_modified_strTr$r%c*t|jS)zi (property) Size of the blob file as a human-readable string. Example: "42.2K".  _format_sizerr s r"size_on_disk_strzCachedFileInfo.size_on_disk_str^D-...r%N) __name__ __module__ __qualname____doc__str__annotations__rintfloatpropertyr#r'r+r%r"rr's2NNNOOOOOO 9999X99999X9/#///X///r%rceZdZUdZeed<eed<eed<ee ed<eeed<e ed<e defd Z e defd Z e defd Zd S) CachedRevisionInfoa.Frozen data structure holding information about a revision. A revision correspond to a folder in the `snapshots` folder and is populated with the exact tree structure as the repo on the Hub but contains only symlinks. A revision can be either referenced by 1 or more `refs` or be "detached" (no refs). Args: commit_hash (`str`): Hash of the revision (unique). Example: `"9338f7b671827df886678df2bdd7cc7b4f36dffd"`. snapshot_path (`Path`): Path to the revision directory in the `snapshots` folder. It contains the exact tree structure as the repo on the Hub. files: (`frozenset[CachedFileInfo]`): Set of [`~CachedFileInfo`] describing all files contained in the snapshot. refs (`frozenset[str]`): Set of `refs` pointing to this revision. If the revision has no `refs`, it is considered detached. Example: `{"main", "2.4.0"}` or `{"refs/pr/1"}`. size_on_disk (`int`): Sum of the blob file sizes that are symlink-ed by the revision. last_modified (`float`): Timestamp of the last time the revision has been created/modified. > [!WARNING] > `last_accessed` cannot be determined correctly on a single revision as blob files > are shared across revisions. > [!WARNING] > `size_on_disk` is not necessarily the sum of all file sizes because of possible > duplicated files. Besides, only blobs are taken into account, not the (negligible) > size of folders and symlinks. commit_hash snapshot_pathrfilesrefs last_modifiedrc*t|jS)z (property) Timestamp of the last time the revision has been modified, returned as a human-readable string. Example: "2 weeks ago". rr=r s r"last_modified_strz$CachedRevisionInfo.last_modified_str  2333r%c*t|jSzn (property) Sum of the blob file sizes as a human-readable string. Example: "42.2K". r)r s r"r+z#CachedRevisionInfo.size_on_disk_strr,r%c*t|jS)zC (property) Total number of files in the revision. )lenr;r s r"nb_fileszCachedRevisionInfo.nb_filess 4:r%N)r-r.r/r0r1r2rr3 frozensetrr4r5r@r+rFr6r%r"r8r8hs  D ^ $$$$ C. 43444X4/#///X/#Xr%r8c eZdZUdZeed<eed<eed<eed<eed<e e ed<e ed<e ed <e d efd Z e d efd Ze d efd Ze d efdZe d eee ffdZdS)CachedRepoInfoaPFrozen data structure holding information about a cached repository. Args: repo_id (`str`): Repo id of the repo on the Hub. Example: `"google/fleurs"`. repo_type (`Literal["dataset", "model", "space", "kernel"]`): Type of the cached repo. repo_path (`Path`): Local path to the cached repo. size_on_disk (`int`): Sum of the blob file sizes in the cached repo. nb_files (`int`): Total number of blob files in the cached repo. revisions (`frozenset[CachedRevisionInfo]`): Set of [`~CachedRevisionInfo`] describing all revisions cached in the repo. last_accessed (`float`): Timestamp of the last time a blob file of the repo has been accessed. last_modified (`float`): Timestamp of the last time a blob file of the repo has been modified/created. > [!WARNING] > `size_on_disk` is not necessarily the sum of all revisions sizes because of > duplicated files. Besides, only blobs are taken into account, not the (negligible) > size of folders and symlinks. > [!WARNING] > `last_accessed` and `last_modified` reliability can depend on the OS you are using. > See [python documentation](https://docs.python.org/3/library/os.html#os.stat_result) > for more details. repo_id repo_type repo_pathrrF revisions last_accessedr=rc*t|jS)z (property) Last time a blob file of the repo has been accessed, returned as a human-readable string. Example: "2 weeks ago". )rrNr s r"last_accessed_strz CachedRepoInfo.last_accessed_strrAr%c*t|jS)z (property) Last time a blob file of the repo has been modified, returned as a human-readable string. Example: "2 weeks ago". r?r s r"r@z CachedRepoInfo.last_modified_strrAr%c*t|jSrCr)r s r"r+zCachedRepoInfo.size_on_disk_strr,r%c$|jd|jS)z9Canonical `type/id` identifier used across cache tooling./)rKrJr s r"cache_idzCachedRepoInfo.cache_ids.114<111r%c$d|jDS)zQ (property) Mapping between `refs` and revision data structures. c(i|]}|jD]}||Sr6)r<).0revisionrefs r" z'CachedRepoInfo.refs..s)VVV( VVXVVVVr%)rMr s r"r<zCachedRepoInfo.refss WVdnVVVVr%N)r-r.r/r0r1r2 REPO_TYPE_Trr3rGr8r4r5rPr@r+rUdictr<r6r%r"rIrIsR>LLLOOOMMM+,,,, 43444X443444X4/#///X/2#222X2Wd3 223WWWXWWWr%rIceZdZUdZeed<eeed<eeed<eeed<eeed<eZeeed<dZ edzed <e d e fd Z d d Z dS)DeleteCacheStrategyaxFrozen data structure holding the strategy to delete cached revisions or files. This object is not meant to be instantiated programmatically but to be returned by [`~utils.HFCacheInfo.delete_revisions`] or [`~utils.HFCacheInfo.delete_files`]. See documentation for usage example. Args: expected_freed_size (`float`): Expected freed size once strategy is executed. blobs (`frozenset[Path]`): Set of blob file paths to be deleted. refs (`frozenset[Path]`): Set of reference file paths to be deleted. repos (`frozenset[Path]`): Set of entire repo paths to be deleted. snapshots (`frozenset[Path]`): Set of snapshots to be deleted (directory of symlinks). files (`frozenset[Path]`, *optional*): Set of individual snapshot entries to be deleted. Their blobs are deleted only if listed in `blobs`. cache_dir (`Path` or `None`): Cache directory the strategy was computed from. Used to collect shared blobs referenced by repo-local symlinks removed by the deletion. expected_freed_sizeblobsr<repos snapshotsr;N cache_dirrc*t|jS)zt (property) Expected size that will be freed as a human-readable string. Example: "42.2K". )r*r`r s r"expected_freed_size_strz+DeleteCacheStrategy.expected_freed_size_str'sD4555r%cTt}|jtjtj|jrt|j}|jD]?}|dz } ||0#t$rY [!WARNING] > If this method is interrupted, the cache might get corrupted. Deletion order is > implemented so that references and symlinks are deleted before the actual blob > files. > [!WARNING] > This method is irreversible. If executed, cached files are erased and must be > downloaded again. NraT) missing_okrepo) path_typesnapshotrZblobrdzCache deletion done. Saved .)setrdr is_shared_blobs_dirshared_blobs_dirrarbupdateiterdirOSErrorshared_blob_targetaddr;unlink_try_delete_pathrcr<sweep_shared_blobloggerinforf)r!shared_store_paths blob_pathsrL blobs_dirr store_pathpaths r"executezDeleteCacheStrategy.execute0s), > %-*K  *4> : :+ + %TZJ!Z   %/ %%i&7&7&9&9::::D' 7 7 !.!A)T^!\!\\:7&**:666J ) )D KK4K ( ( ( (J 5 5D TV 4 4 4 4 4N 9 9D TZ 8 8 8 8 8I 4 4D TU 3 3 3 3 3J 5 5D TV 4 4 4 4 4 > %0 V V / dnUUUUU Q$2NQQQRRRRRs$'B  BB)rN)r-r.r/r0r3r2rGrr;rdr5r1rfrr6r%r"r_r_s2 T? D/ T?&Y[[E9T?(((!Itd{!!! 6666X69S9S9S9S9S9Sr%r_c(eZdZUdZeed<eed<dS)CachedIncompleteFileInfoaFrozen data structure holding information about a single incomplete download. Interrupted downloads leave `//blobs/.incomplete` files behind. These are not part of any committed revision, so they are surfaced separately by [`scan_cache_dir`]. Args: file_path (`Path`): Path of the `.incomplete` file in the `blobs` folder. size_on_disk (`int`): Size of the partially-downloaded file in bytes. rrN)r-r.r/r0rr2r3r6r%r"rrls3  OOOr%rceZdZUdZeed<eeed<eeed<e e ed<dZ e dzed<e defd Ze defd Zd edefd Zd edefdZdddedefdZdS) HFCacheInfoaFrozen data structure holding information about the entire cache-system. This data structure is returned by [`scan_cache_dir`] and is immutable. Args: size_on_disk (`int`): Physical size of the cache-system in bytes. A blob shared across repos is counted once, and store-only shared blobs no longer referenced by any repo are included. Can be smaller than the sum of the per-repo sizes. repos (`frozenset[CachedRepoInfo]`): Set of [`~CachedRepoInfo`] describing all valid cached repos found on the cache-system while scanning. incomplete_files (`frozenset[CachedIncompleteFileInfo]`): Set of [`~CachedIncompleteFileInfo`] describing orphaned `*.incomplete` files left behind by interrupted downloads. warnings (`list[CorruptedCacheException]`): List of [`~CorruptedCacheException`] that occurred while scanning the cache. Those exceptions are captured so that the scan can continue. Corrupted repos are skipped from the scan. cache_dir (`Path` or `None`): Cache directory that was scanned. > [!WARNING] > `size_on_disk` only accounts for blobs, and corrupted repos are skipped. It is a > physical size: unlike `CachedRepoInfo.size_on_disk`, which attributes a shared blob > to every repo referencing it, a shared blob is counted here only once. rrbincomplete_fileswarningsNrdrc*t|jS)zu (property) Physical size of the cache-system as a human-readable string. Example: "42.2K". r)r s r"r+zHFCacheInfo.size_on_disk_strr,r%c>td|jDS)z9(property) Sum of all incomplete download sizes in bytes.c3$K|] }|jV dSN)rrXfiles r" z6HFCacheInfo.incomplete_size_on_disk..s%GG4$GGGGGGr%)sumrr s r"incomplete_size_on_diskz#HFCacheInfo.incomplete_size_on_disks$GG1FGGGGGGr%rMc t|}tt}|jD]J}|jD]@}|j|vr5|||||jAKt|dkr0t dd |t}t}t}t} i} | D]\} } | j| z } t| dkr>|| j | jD]}|j D]}|j| |j<ad| D}| D]}| |j|jD]"}|| j dz |z #|j D]W}|j|jjvr|j| |j<%|j|vr)||j|j| |j<Xt't)|t)|t)|t)| t+| |j|jS)aPrepare the strategy to delete one or more revisions cached locally. Input revisions can be any revision hash. If a revision hash is not found in the local cache, a warning is thrown but no error is raised. Revisions can be from different cached repos since hashes are unique across repos, Examples: ```py >>> from huggingface_hub import scan_cache_dir >>> cache_info = scan_cache_dir() >>> delete_strategy = cache_info.delete_revisions( ... "81fd1d6e7847c99f5862c9fb81387956d99ec7aa" ... ) >>> print(f"Will free {delete_strategy.expected_freed_size_str}.") Will free 7.9K. >>> delete_strategy.execute() Cache deletion done. Saved 7.9K. ``` ```py >>> from huggingface_hub import scan_cache_dir >>> scan_cache_dir().delete_revisions( ... "81fd1d6e7847c99f5862c9fb81387956d99ec7aa", ... "e2983b237dccf3ab4937c97fa717319a9ca1a96d", ... "6c0e6080953db56375760c0471a8c5f2929baf11", ... ).execute() Cache deletion done. Saved 8.6G. ``` > [!WARNING] > `delete_revisions` returns a [`~utils.DeleteCacheStrategy`] object that needs to > be executed. The [`~utils.DeleteCacheStrategy`] is not meant to be modified but > allows having a dry run before actually executing the deletion. rz,Revision(s) not found - cannot delete them: , c0h|]}|jD] }|j Sr6)r;r)rXrYrev_files r" z/HFCacheInfo.delete_revisions..s-rrrxckcqrrW_ 2rrrrr%r<)rar<rbrcr`rd)rorrbrMr9rvremoverErzwarningjoinitemsrLr;rrr:r<parentsr_rG_expected_freed_sizerd)r!rMhashes_to_deleterepos_with_revisionsrirYdelete_strategy_blobsdelete_strategy_refsdelete_strategy_reposdelete_strategy_snapshotsblobs_to_unlink affected_reporevisions_to_deleteother_revisionsrother_blob_pathsrevision_to_deleterZs r"delete_revisionszHFCacheInfo.delete_revisionssF&)^^NYZ]N^N^J B BD N B B'+;;;(.228<<<$++H,@AAA B  1 $ $ NNg$))TdJeJegg h h h+.55*-%%+.55/2uu!,.2F2L2L2N2N% L% L .M.+58KKO?##q((%))-*ABBB - 7LLH (LL:>:K77L sr?rrr &9 L L")--.@.NOOO.2UUC(,,]-Dv-MPS-STTTT/4 L LD *74>;QQQ:>:K7 ~-===-11$.AAA:>:K7 L L2#122/00122 9:: 4_dn U Un     r%r;c t|fd|jDfdD}tdD}tt ||jt||z ttt||jS)a=Prepare the strategy to delete individual cached files. Only the snapshot entries are removed. A blob is deleted only if no other cached file references it, so blobs shared with other revisions are kept. Refs and snapshot directories are kept as well, even if a snapshot ends up empty. To delete whole revisions or repos, use [`~utils.HFCacheInfo.delete_revisions`]. Example: ```py >>> from huggingface_hub import scan_cache_dir >>> cache_info = scan_cache_dir() >>> files = [ ... file ... for repo in cache_info.repos ... if repo.repo_id == "org/model" ... for revision in repo.revisions ... for file in revision.files ... if file.file_name == "model-Q4_K_M.gguf" ... ] >>> delete_strategy = cache_info.delete_files(*files) >>> print(f"Will free {delete_strategy.expected_freed_size_str}.") Will free 4.9G. >>> delete_strategy.execute() Cache deletion done. Saved 4.9G. ``` cNh|]!}|jD]}|jD] }|v|j"Sr6)rMr;r)rXrirYrselecteds r"rz+HFCacheInfo.delete_files..6s`    N      8## N$####r%c<i|]}|jv |j|jSr6)rr)rXrretained_blobss r"r[z,HFCacheInfo.delete_files..=s4   26dn\jFjFjDND-FjFjFjr%c3$K|] }|jV dSr)rrs r"rz+HFCacheInfo.delete_files..@s$CC$t~CCCCCCr%)r`rar<rbrcr;rd)rorbrGr_rrdkeys)r!r;r file_pathsrrs @@r" delete_fileszHFCacheInfo.delete_filess6u::            :B   CC(CCCCC " 4_dn U UO0022Z?@@++kkn    r%r) verbosityrc|dkr2tdt|jdDgdStdt|jdDgd S) a} Generate a table from the [`HFCacheInfo`] object. Pass `verbosity=0` to get a table with a single row per repo, with columns "repo_id", "repo_type", "size_on_disk", "nb_files", "last_accessed", "last_modified", "refs", "local_path". Pass `verbosity=1` to get a table with a row per repo and revision (thus multiple rows can appear for a single repo), with columns "repo_id", "repo_type", "revision", "size_on_disk", "nb_files", "last_modified", "refs", "local_path". Example: ```py >>> from huggingface_hub.utils import scan_cache_dir >>> hf_cache_info = scan_cache_dir() HFCacheInfo(...) >>> print(hf_cache_info.export_as_table()) REPO ID REPO TYPE SIZE ON DISK NB FILES LAST_ACCESSED LAST_MODIFIED REFS LOCAL PATH --------------------------------------------------- --------- ------------ -------- ------------- ------------- ---- -------------------------------------------------------------------------------------------------- roberta-base model 2.7M 5 1 day ago 1 week ago main ~/.cache/huggingface/hub/models--roberta-base suno/bark model 8.8K 1 1 week ago 1 week ago main ~/.cache/huggingface/hub/models--suno--bark t5-base model 893.8M 4 4 days ago 7 months ago main ~/.cache/huggingface/hub/models--t5-base t5-large model 3.0G 4 5 weeks ago 5 months ago main ~/.cache/huggingface/hub/models--t5-large >>> print(hf_cache_info.export_as_table(verbosity=1)) REPO ID REPO TYPE REVISION SIZE ON DISK NB FILES LAST_MODIFIED REFS LOCAL PATH --------------------------------------------------- --------- ---------------------------------------- ------------ -------- ------------- ---- ----------------------------------------------------------------------------------------------------------------------------------------------------- roberta-base model e2da8e2f811d1448a5b465c236feacd80ffbac7b 2.7M 5 1 week ago main ~/.cache/huggingface/hub/models--roberta-base/snapshots/e2da8e2f811d1448a5b465c236feacd80ffbac7b suno/bark model 70a8a7d34168586dc5d028fa9666aceade177992 8.8K 1 1 week ago main ~/.cache/huggingface/hub/models--suno--bark/snapshots/70a8a7d34168586dc5d028fa9666aceade177992 t5-base model a9723ea7f1b39c1eae772870f3b547bf6ef7e6c1 893.8M 4 7 months ago main ~/.cache/huggingface/hub/models--t5-base/snapshots/a9723ea7f1b39c1eae772870f3b547bf6ef7e6c1 t5-large model 150ebc2c4b72291e770f58e6057481c8d2ed331a 3.0G 4 5 months ago main ~/.cache/huggingface/hub/models--t5-large/snapshots/150ebc2c4b72291e770f58e6057481c8d2ed331a ``` Args: verbosity (`int`, *optional*): The verbosity level. Defaults to 0. Returns: `str`: The table as a string. rc g|]c}|j|j|jd|j|j|jdt|jt|j gdS)>12r) rJrKr+rFrPr@rsortedr<r1rL)rXris r" z/HFCacheInfo.export_as_table..vsy    066 .. &"3"344DN++    r%c|jSrrLris r"z-HFCacheInfo.export_as_table..DNr%key)REPO ID REPO TYPE SIZE ON DISKNB FILES LAST_ACCESSED LAST_MODIFIEDREFS LOCAL PATH)rowsheaderscg|]}}t|jdD]c}|j|j|j|jd|j|jdt|j t|j gd~S)c|jSr)r9)rYs r"rz8HFCacheInfo.export_as_table...s PXPdr%rrr) rrMrJrKr9r+rFr@rr<r1r:)rXrirYs r"rz/HFCacheInfo.export_as_table..s   $*4>?d?d$e$e$e  !  ,#4:: ) 2 &"7"788H233     r%c|jSrrrs r"rz-HFCacheInfo.export_as_table..rr%)rrREVISIONrrrrr)rrrb)r!rs r"export_as_tablezHFCacheInfo.export_as_tableLsP >>  !'tz7R7R S S S       4  !'tz7R7R S S S       r%)r-r.r/r0r3r2rGrIrlistrrdrr5r1r+rr_rrrrr6r%r"rrsQ8 ^ $$$$ 89999*++++!Itd{!!! /#///X/HHHHXHg 3g 3Fg g g g R0 >0 6I0 0 0 0 d34\\\C\\\\\\\r%rrdrc ttst ddrtddt}g} D]}|j tvr|j dkr|j dkr)|j tj krtj|rS |t!|w#t"$r}||Yd}~d}~wwxYwtjtj fd|D}|tjz}d }|D]/} ||jz } #t.$rY,wxYwt1t3||t5| S) a Scan the entire HF cache-system and return a [`~HFCacheInfo`] structure. Use `scan_cache_dir` in order to programmatically scan your cache-system. The cache will be scanned repo by repo. If a repo is corrupted, a [`~CorruptedCacheException`] will be thrown internally but captured and returned in the [`~HFCacheInfo`] structure. Only valid repos get a proper report. ```py >>> from huggingface_hub import scan_cache_dir >>> hf_cache_info = scan_cache_dir() HFCacheInfo( size_on_disk=3398085269, repos=frozenset({ CachedRepoInfo( repo_id='t5-small', repo_type='model', repo_path=PosixPath(...), size_on_disk=970726914, nb_files=11, revisions=frozenset({ CachedRevisionInfo( commit_hash='d78aea13fa7ecd06c29e3e46195d6341255065d5', size_on_disk=970726339, snapshot_path=PosixPath(...), files=frozenset({ CachedFileInfo( file_name='config.json', size_on_disk=1197 file_path=PosixPath(...), blob_path=PosixPath(...), ), CachedFileInfo(...), ... }), ), CachedRevisionInfo(...), ... }), ), CachedRepoInfo(...), ... }), warnings=[ CorruptedCacheException("Snapshots dir doesn't exist in cached repo: ..."), CorruptedCacheException(...), ... ], ) ``` You can also print a detailed report directly from the `hf` command line using: ```text > hf cache ls ID SIZE LAST_ACCESSED LAST_MODIFIED REFS --------------------------- -------- ------------- ------------- ----------- dataset/nyu-mll/glue 157.4M 2 days ago 2 days ago main script model/LiquidAI/LFM2-VL-1.6B 3.2G 4 days ago 4 days ago main model/microsoft/UserLM-8b 32.1G 4 days ago 4 days ago main Done in 0.0s. Scanned 6 repo(s) for a total of 3.4G. Got 1 warning(s) while scanning. Use -vvv to print details. ``` Args: cache_dir (`str` or `Path`, `optional`): Cache directory to cache. Defaults to the default HF cache directory. > [!WARNING] > Raises: > > `CacheNotFound` > If the cache directory does not exist. > > [`ValueError`](https://docs.python.org/3/library/exceptions.html#ValueError) > If the cache directory is a file, instead of a directory. Returns: a [`~HFCacheInfo`] object. NzCache directory not found: zM. Please use `cache_dir` argument or set `HF_HUB_CACHE` environment variable.rmz1Scan cache expects a directory but found a file: z.locksz CACHEDIR.TAGc~h|]9}|jD]/}|jD]%}rtj|j|j&0:Sr)rMr;r rur)rXrirYrrd store_markeds r"rz!scan_cache_dir..sv  N    -?PYZZb  cbbbbr%r)rbrrrrd)r r expanduserresolveexistsris_file ValueErrorrorsnameFILES_TO_IGNOREr SHARED_BLOBS_DIR_NAMErprv_scan_cached_reporappendrqshared_store_blob_pathsstatst_sizertrrG_scan_incomplete_files) rdrbrrLerepo_blob_pathsphysical_blob_paths physical_sizerrs ` @r"scan_cache_dirrs` Y**,,4466I       C) C C C      Y Y Y Y   "%E.0H&&((   >_ , ,  >X % %  >^ + +  >]@ @ @]EfgpEqEq @   II' 22 3 3 3 3&    OOA          !4]5ST]5^5^__LO*M,QR[,\,\\M(   Y^^--5 5MM    D  "/ ::    s*"D** E4EE)G GGc t}|dD]Q} |j}n#t$rY)wxYw|t ||Rt|S)a,Find orphaned `*.incomplete` partial-download files in the cache. Interrupted downloads leave `//blobs/.incomplete` files behind. These are not part of any committed revision, so they are reported separately in the [`~HFCacheInfo`] returned by [`scan_cache_dir`]. z*/blobs/*.incomplete)rr)roglobrrrtrvrrG)rdr;rrs r"rr5s,/55E566WW 99;;.LL    H  *T UUUVVVV U  sA A ArLc |std|d|jvrtd||jdd\}}|dd}|t vr+tdt t d|d |d t |}i|d z }|d z }|r|std |tt}|r| rtd|| dD]}|s|jtvr%| |}|5} | } dddn #1swxYwY|| |t} |D]8} | jtvr| rtd| t} | dD]}|r|rGt)t*j|jt+j|z }n|}|std||vr||<| t7|j||j||j|jt?| dkrtAfd| D}n| j}| tC| jtE| tE|#| jttIfdd| DD| |:t?|dkr#tdtK|d|d t?dkrWtAd&D}tAd&D}n"|}|j}|j}tOt?|||tE| tId&D||S)zScan a single cache repo and return information about it. Any unexpected behavior will raise a [`~CorruptedCacheException`]. zRepo path is not a directory: z--z6Repo path is not a valid HuggingFace cache directory: r )maxsplitrTzRepo type must be one of z , found `z` (z).rcr<z,Snapshots dir doesn't exist in cached repo: z!Refs directory cannot be a file: z**/*Nz*Snapshots folder corrupted. Found a file: zBlob missing (broken symlink): )rrrrrrrc3<K|]}|jjVdSr)rst_mtime)rXr blob_statss r"rz$_scan_cached_repo..s.(f(fQUDN)C)L(f(f(f(f(f(fr%c32K|]}|jVdSrr)rXrrs r"rz$_scan_cached_repo..s<!!6?Jy)1!!!!!!r%ch|] }|j Sr6)rrs r"rz$_scan_cached_repo..sClClClW[DNClClClr%)r9r;r<rr:r=z-Reference(s) refer to missing commit hashes: z (c3$K|] }|jV dSr)st_atimerXrs r"rz$_scan_cached_repo..$ O O4 O O O O O Or%c3$K|] }|jV dSr)rrs r"rz$_scan_cached_repo..rr%c3$K|] }|jV dSrrrs r"rz$_scan_cached_repo..s$FF$FFFFFFr%)rFrJrLrKrMrrNr=)(is_dirrrsplitreplacer rrrrorrr relative_toas_posixopenreadrvrs is_symlinkrosrabspathparentreadlinkrrrrrrEmaxr8rGpoprr]valuesrI)rLrepo_type_prefixrJrKsnapshots_path refs_path refs_by_hashref_pathref_namefr9cached_revisions revision_path cached_filesrrrevision_last_modifiedrepo_last_accessedrepo_last_modified repo_statsrs @r"rrFs1     T%&Ry&R&RSSS 9>!!%&j_h&j&jkkk ) 4 4TA 4 F FgoodC((G111% o/A(B(B o oM] o obk o o o   ##34I-/J,NF"I  " "g.*?*?*A*Ag%&eUc&e&efff )4C(8(8L4      [)*Yi*Y*YZZ Z!v.. 4 4H   HM_$D$D++I66??AAH 'Affhh  ' ' ' ' ' ' ' ' ' ' ' ' ' ' '  % ) )( 3 3 3 314'//116 6   0 0   " " h)*fWd*f*fgg guu &++F33  I!! ##%% & 1ABKPYDZDZ1Z![![\\ % ##%% ]-.[PY.[.[\\\ **(1(8(8 9%   'n'!+I!6!>''1)'<'E'1)'<'E      |  q %((f(f(f(fYe(f(f(f%f%f " "%2%7%7%9%9%B " ). --|// 0BCEEJJKK !!!!ClCl_kClClCl!!!,4     <1% _D> T__.. IdOOOOO M$      PPP N)NNtNNNOOOOOO bbbQ)QQ$QQQ\`aaaaaabsr4s;: ######!!!!!!IIIIIIII88888888$$$$$$$$&&&&&&  H % %;< <;; $=/=/=/=/=/=/=/=/@ $CCCCCCCCL $QWQWQWQWQWQWQWQWh $dSdSdSdSdSdSdSdSN $$ $hhhhhhhhV GGcDj4/G;GGGGTdy9Q/R"II.IIIIX c c    $tSy/dTkVY0b4bCbDbbbbbbr%