o
Zh{r @ s d Z ddlZddlZddlZddlmZ ddlmZ ddlm Z ddl
m Z m Z m
Z
mZmZmZmZ ddlmZ d d
lmZ eeZed Zd gZG d
d deZ G dd deZ eddG dd dZ eddG dd dZ eddG dd dZ eddG dd dZ!eddG dd d Z"d/d eee#e f d e"fd d Z$d!e d e fd"d#Z%d$e&d e#fd%d&Z'd'Z(d(e)d e#fd)d*Z*d+e d,e#d dfd-d.Z+dS )0z4Contains utilities to manage the HF cache directory. N) defaultdict) dataclass)Path)Dict FrozenSetListLiteralOptionalSetUnion ) HF_HUB_CACHE )logging)modeldatasetspacez .DS_Storec sD e Zd ZU dZeeef ed< dedeeef f fdd Z Z S )
CacheNotFoundz9Exception thrown when the Huggingface cache is not found. cache_dirmsgc s$ t j|g|R i | || _d S N)super__init__r )selfr r argskwargs __class__ [/var/www/html/lang_env/lib/python3.10/site-packages/huggingface_hub/utils/_cache_manager.pyr * s
zCacheNotFound.__init__)
__name__
__module__ __qualname____doc__r strr __annotations__r
__classcell__r r r r r % s
&r c @ s e Zd ZdZdS )CorruptedCacheExceptionzGException for any unexpected structure in the Huggingface cache-system.N)r r! r" r# r r r r r' / s r' T)frozenc @ sx e Zd ZU dZeed< eed< eed< eed< eed< eed< e defd d
Z
e defd d Z e defd
dZ dS )CachedFileInfoa Frozen 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 blob file. This is equivalent to `file_path.resolve()`.
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.
`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 C
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".
)_format_timesincer. r r r r blob_last_accessed_strX
z%CachedFileInfo.blob_last_accessed_strc C r1 )z
(property) Timestamp of the last time the blob file has been modified, returned
as a human-readable string.
Example: "2 weeks ago".
)r2 r/ r3 r r r blob_last_modified_strb r5 z%CachedFileInfo.blob_last_modified_strc C r1 )zi
(property) Size of the blob file as a human-readable string.
Example: "42.2K".
_format_sizer- r3 r r r size_on_disk_strl
z CachedFileInfo.size_on_disk_strN)
r r! r" r# r$ r% r intfloatpropertyr4 r6 r9 r r r r r) 3 s
r) c @ s e Zd ZU dZeed< eed< eed< ee ed< ee ed< e
ed< e defd d
Z e defd d Z
e defd
dZdS )CachedRevisionInfoaN 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.
`last_accessed` cannot be determined correctly on a single revision as blob files
are shared across revisions.
`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_pathr- filesrefs
last_modifiedr0 c C r1 )z
(property) Timestamp of the last time the revision has been modified, returned
as a human-readable string.
Example: "2 weeks ago".
r2 rC r3 r r r last_modified_str r5 z$CachedRevisionInfo.last_modified_strc C r1 zn
(property) Sum of the blob file sizes as a human-readable string.
Example: "42.2K".
r7 r3 r r r r9 r: z#CachedRevisionInfo.size_on_disk_strc C r1 )zC
(property) Total number of files in the revision.
)lenrA r3 r r r nb_files s
zCachedRevisionInfo.nb_filesN)r r! r" r# r$ r% r r; r r) r< r= rE r9 rH r r r r r> v s
( r> c @ s e Zd ZU dZeed< eed< eed< eed< eed< e e
ed< e ed< e ed < e d
efd d Z
e d
efd
dZe d
efddZe d
eee
f fddZdS )CachedRepoInfoad Frozen 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"]`):
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.
`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.
`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_pathr- rH revisions
last_accessedrC r0 c C r1 )z
(property) Last time a blob file of the repo has been accessed, returned as a
human-readable string.
Example: "2 weeks ago".
)r2 rN r3 r r r last_accessed_str r5 z CachedRepoInfo.last_accessed_strc C r1 )z
(property) Last time a blob file of the repo has been modified, returned as a
human-readable string.
Example: "2 weeks ago".
rD r3 r r r rE r5 z CachedRepoInfo.last_modified_strc C r1 rF r7 r3 r r r r9 r: z CachedRepoInfo.size_on_disk_strc C s dd | j D S )zQ
(property) Mapping between `refs` and revision data structures.
c S s i | ] }|j D ]}||qqS r )rB ).0revisionrefr r r
s z'CachedRepoInfo.refs..)rM r3 r r r rB s zCachedRepoInfo.refsN)r r! r" r# r$ r% REPO_TYPE_Tr r; r r> r< r= rO rE r9 r rB r r r r rI s$
% rI c @ sf e Zd ZU dZeed< ee ed< ee ed< ee ed< ee ed< ede fdd Z
d
d d Z d
S )DeleteCacheStrategya Frozen data structure holding the strategy to delete cached revisions.
This object is not meant to be instantiated programmatically but to be returned by
[`~utils.HFCacheInfo.delete_revisions`]. 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).
expected_freed_sizeblobsrB repos snapshotsr0 c C r1 )zt
(property) Expected size that will be freed as a human-readable string.
Example: "42.2K".
)r8 rV r3 r r r expected_freed_size_str3 r: z+DeleteCacheStrategy.expected_freed_size_strNc C sx | j D ]}t|dd q| jD ]}t|dd q| jD ]}t|dd q| jD ]}t|dd q'td| j d dS ) a Execute the defined strategy.
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.
This method is irreversible. If executed, cached files are erased and must be
downloaded again.
repo) path_typeZsnapshotrR ZblobzCache deletion done. Saved .N)rX _try_delete_pathrY rB rW loggerinforZ )r pathr r r execute< s
zDeleteCacheStrategy.execute)r0 N) r r! r" r# r; r% r r r= r$ rZ rb r r r r rU s
rU c @ sV e Zd ZU dZeed< ee ed< ee ed< e
de fddZ de de
fd d
Zd S ) HFCacheInfoa Frozen 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`):
Sum of all valid repo sizes in the cache-system.
repos (`FrozenSet[CachedRepoInfo]`):
Set of [`~CachedRepoInfo`] describing all valid cached repos found on the
cache-system while scanning.
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.
Here `size_on_disk` is equal to the sum of all repo sizes (only blobs). However if
some cached repos are corrupted, their sizes are not taken into account.
r- rX warningsr0 c C r1 )z
(property) Sum of all valid repo sizes in the cache-system as a human-readable
string.
Example: "42.2K".
r7 r3 r r r r9 r5 z HFCacheInfo.size_on_disk_strrM c G s t |}tt }| jD ]}|jD ]}|j|v r$|| | ||j qq t|dkr7t dd
| t }t }t }t } d}
| D ]i\} } | j| }
t|
dkrd|| j |
| j
7 }
qI| D ]K}| |j |jD ] }|| j d | qq|jD ]/}|j|vrd}|
D ]}|jD ] }|j|jkrd} nq|s nq|r||j |
|j
7 }
qqfqItt|t|t|t| |
dS )a Prepare the strategy to delete one or more revisions cached locally.
Input revisions can be any revision hash. If a revision hash is not found in the
local cache, a warning is thrown but no error is raised. Revisions can be from
different cached repos since hashes are unique across repos,
Examples:
```py
>>> from huggingface_hub import scan_cache_dir
>>> cache_info = scan_cache_dir()
>>> delete_strategy = cache_info.delete_revisions(
... "81fd1d6e7847c99f5862c9fb81387956d99ec7aa"
... )
>>> print(f"Will free {delete_strategy.expected_freed_size_str}.")
Will free 7.9K.
>>> delete_strategy.execute()
Cache deletion done. Saved 7.9K.
```
```py
>>> from huggingface_hub import scan_cache_dir
>>> scan_cache_dir().delete_revisions(
... "81fd1d6e7847c99f5862c9fb81387956d99ec7aa",
... "e2983b237dccf3ab4937c97fa717319a9ca1a96d",
... "6c0e6080953db56375760c0471a8c5f2929baf11",
... ).execute()
Cache deletion done. Saved 8.6G.
```
`delete_revisions` returns a [`~utils.DeleteCacheStrategy`] object that needs to
be executed. The [`~utils.DeleteCacheStrategy`] is not meant to be modified but
allows having a dry run before actually executing the deletion.
r z,Revision(s) not found - cannot delete them: z, rB TF)rW rB rX rY rV )setr rX rM r? addremoverG r_ warningjoinitemsrL r- r@ rB rA r, rU frozenset)r rM Zhashes_to_deleteZrepos_with_revisionsr[ rQ Zdelete_strategy_blobsZdelete_strategy_refsZdelete_strategy_reposZdelete_strategy_snapshotsZ#delete_strategy_expected_freed_sizeZ
affected_repoZrevisions_to_deleteZother_revisionsZrevision_to_deleterR fileZ
is_file_aloneZrev_filer r r delete_revisions sf &
z HFCacheInfo.delete_revisionsN)r r! r" r# r; r% r rI r r' r= r$ r9 rU rm r r r r rc e s
rc r r0 c C s | du rt } t| } | s td| d| d| r(td| dt }g }| D ](}|j
dkr9q1z | t | W q1 t
yY } z || W Y d}~q1d}~ww tt|tdd |D |d S )
at 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 `huggingface-cli` using:
```text
> huggingface-cli scan-cache
REPO ID REPO TYPE SIZE ON DISK NB FILES REFS LOCAL PATH
--------------------------- --------- ------------ -------- ------------------- -------------------------------------------------------------------------
glue dataset 116.3K 15 1.17.0, main, 2.4.0 /Users/lucain/.cache/huggingface/hub/datasets--glue
google/fleurs dataset 64.9M 6 main, refs/pr/1 /Users/lucain/.cache/huggingface/hub/datasets--google--fleurs
Jean-Baptiste/camembert-ner model 441.0M 7 main /Users/lucain/.cache/huggingface/hub/models--Jean-Baptiste--camembert-ner
bert-base-cased model 1.9G 13 main /Users/lucain/.cache/huggingface/hub/models--bert-base-cased
t5-base model 10.1K 3 main /Users/lucain/.cache/huggingface/hub/models--t5-base
t5-small model 970.7M 11 refs/pr/1, main /Users/lucain/.cache/huggingface/hub/models--t5-small
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.
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.)r z1Scan cache expects a directory but found a file: z.locksc s | ]}|j V qd S r )r- )rP r[ r r r e z!scan_cache_dir..)rX r- rd )r
r
expanduserresolveexistsr is_file
ValueErrorre iterdirnamerf _scan_cached_repor' appendrc rk sum)r rX rd rL er r r scan_cache_dir s8 V
r| rL c s | s td| d| jvrtd| | jjddd\}}|dd }|dd}|d vr r r r z8Repo type must be `dataset`, `model` or `space`, found `z` (z).rY rB z,Snapshots dir doesn't exist in cached repo: z!Refs directory cannot be a file: z**/*z*Snapshots folder corrupted. Found a file: z Blob missing (broken symlink): )r* r+ r- r, r. r/ r c 3 s | ] } |j jV qd S r )r, st_mtimerP rl Z
blob_statsr r ro s z$_scan_cached_repo..c 3 s | ]} | j V qd S r st_size)rP r, r r r ro s
c s rn r )r, r r r r ro rp )r? rA rB r- r@ rC z-Reference(s) refer to missing commit hashes: z (c s rn r )st_atimerP statr r r ro rp c s rn r )r r r r r ro rp c s rn r r r r r r ro rp )rH rJ rL rK rM r- rN rC )!is_dirr' rw splitreplacers r re rt globr$ relative_toopenreadrf rv FILES_TO_IGNOREr rr r r) r r r rG maxr> rk poprz dictvaluesrI )rL rK rJ Zsnapshots_pathZ refs_pathZ refs_by_hashZref_pathref_namefr? Zcached_revisionsZ
revision_path cached_filesr+ r, Zrevision_last_modifiedZrepo_last_accessedZrepo_last_modifiedZ
repo_statsr r r rx j s
rx numc C sD t | }dD ]}t|dk r|d| S |d }q|ddS )zkFormat size in bytes into a human-readable string.
Taken from https://stackoverflow.com/a/1094933
) KMGTPEZg @@z3.1fz.1fY)r< abs)r Znum_funitr r r r8 s
r8 ))secondr < )minuter r )houri )dayiQ )weeki: r )monthi ' )yeari3Ntsc C sn t | }|dk r dS tD ]\}}}t|| }|dur#||kr# nq| d| |dkr2d dS d dS ) zFormat timestamp in seconds into a human-readable string, relative to now.
Vaguely inspired by Django's `timesince` formatter.
za few seconds agoN r sr z ago)time_TIMESINCE_CHUNKSround)r deltalabeldividerZ max_valuevaluer r r r2
s &r2 ra r\ c C s t d| d| z| rt| W d S t| W d S ty7 t jd| d| ddd Y d S t yN t jd| d| ddd Y d S w )
aE Try to delete a local file or folder.
If the path does not exists, error is logged as a warning and then ignored.
Args:
path (`Path`)
Path to delete. Can be a file or a folder.
path_type (`str`)
What path are we deleting ? Only for logging purposes. Example: "snapshot".
zDelete z: zCouldn't delete z: file not found ()T)exc_infoz: permission denied (N)
r_ r` rt osrg shutilrmtreeFileNotFoundErrorrh PermissionError)ra r\ r r r r^ s " "r^ r ),r# r r r collectionsr dataclassesr pathlibr typingr r r r r r
r constantsr
r r Z
get_loggerr r_ rT r Exceptionr r' r) r> rI rU rc r$ r| rx r; r8 r r< r2 r^ r r r r sB $
BLUK v