o U h [ @sdZddlZddlmZmZddlmZddlmZddl m Z ddl m Z dd l mZmZmZmZmZd Zd Zd Zd ZdZdZeefZedddZdZdZdZdZGdddedgdZde dede!efddZ"de dedede!e#eeffddZ$dd Z%d>d"d#Z&d$d%Z' !  ! !d?d&d'Z(de)fd(d)Z*d*d+Z+ d@d,e d-e!ed.efd/d0Z,d1Z-d2ede.e/e/ffd3d4Z0d5d6Z1d@d7d8Z2d9d:Z3Gd;d<d<Z4e%Z5e$Z6e0Z7z dd=l8m0Z0m%Z%m$Z$WdSe9yYdSw)Az&Utilities for diffing files and trees.N) defaultdict namedtuple)BytesIO)chain)Optional)BaseObjectStore) S_ISGITLINKObjectIDShaFileTree TreeEntryaddmodifydeleterenamecopy unchangedd<c@s(eZdZdZeddZeddZdS) TreeChangez.Named tuple a single change between two trees.cCs |tt|SN) CHANGE_ADD _NULL_ENTRY)clsnewre/var/www/html/construction_image-detection-poc/venv/lib/python3.10/site-packages/dulwich/diff_tree.pyr6 zTreeChange.addcCs |t|tSr) CHANGE_DELETEr)roldrrrr:rzTreeChange.deleteN)__name__ __module__ __qualname____doc__ classmethodrrrrrrr3s  r)typer!rpathtreereturncCs2g}|s|S|jddD] }|||q |S)NT) name_order) iteritemsappendin_path)r(r)resultentryrrr _tree_entries?s r1tree1tree2c Cst||}t||}d}}t|}t|}g} ||krc||krc||} ||} | j| jkr:| | tf|d7}n!| j| jkrL| t| f|d7}n| | | f|d7}|d7}||krc||ks t||D] } | || tfqht||D] } | t|| fqy| S)aMerge the entries of two trees. Args: path: A path to prepend to all tree entry names. tree1: The first Tree object to iterate, or None. tree2: The second Tree object to iterate, or None. Returns: A list of pairs of TreeEntry objects for each pair of entries in the trees. If an entry exists in one tree but not the other, the other entry will have all attributes set to None. If neither entry's path is None, they are guaranteed to match. rr)r1lenr(r-rrange) r(r2r3entries1entries2i1i2len1len2r/entry1entry2irrr_merge_entriesHs0       r?cCs|j}|dur dSt|SNF)modestatS_ISDIR)r0rArrr_is_treess rDFccs|rtjpd}|r tjpd}td||td||fg}|rc|\}}t|} t|} |r7| r7| r7||kr7q| r>||jp?d} | rG||jpHd} |jpN|j} |tt | | | ||fV|sdSdS)aRecursively walk all the entries of two trees. Iteration is depth-first pre-order, as in e.g. os.walk. Args: store: An ObjectStore for looking up objects. tree1_id: The SHA of the first Tree object to iterate, or None. tree2_id: The SHA of the second Tree object to iterate, or None. prune_identical: If True, identical subtrees will not be walked. Returns: Iterator over Pairs of TreeEntry objects for each pair of entries in the trees and their subtrees recursively. If an entry exists in one tree but not the other, the other entry will have all attributes set to None. If neither entry's path is None, they are guaranteed to match. N) rBS_IFDIRr poprDshar(extendreversedr?)storetree1_idtree2_idprune_identicalmode1mode2todor<r=is_tree1is_tree2r2r3r(rrr walk_treeszs     rTcCs"|jdus |st|jrtS|Sr)rArBrCr)r0 include_treesrrr _skip_treesrVc cs|dur|dur|dur|j||||dEdHdSt|||| d}|D]V\}} || kr1|s1q&t||}t| |} |tkrf| tkrft|jt| jkr\|s\t|Vt}t } n|| krct } nt } n|tkrmt } n| tkrtt } nq&t| || Vq&dS)avFind the differences between the contents of two trees. Args: store: An ObjectStore for looking up objects. tree1_id: The SHA of the source tree. tree2_id: The SHA of the target tree. want_unchanged: If True, include TreeChanges for unmodified entries as well. include_trees: Whether to include trees rename_detector: RenameDetector object for detecting renames. change_type_same: Whether to report change types in the same entry or as delete+add. Returns: Iterator over TreeChange instances for each change between the source and target tree. Nwant_unchangedrU)rN) changes_with_renamesrTrVrrBS_IFMTrArrrCHANGE_UNCHANGED CHANGE_MODIFYr ) rKrLrMrXrename_detectorrUchange_type_sameentriesr<r= change_typerrr tree_changessD       racCs |D] }|||kr dSqdS)NFTr)seqkeyvalueerrr_all_eqs  rfcCst|dd|||dS)Nrr)rf)rbrcrrr _all_samesrgrKparent_tree_idstree_idc#sfdd|D}t|tfdd}t|D]\}}|D]}|jtkr.|jj} n|jj} ||| |<q"qdd} dd} t| D]2\} } t| ksTJd d| D}t || trjt || si| VqHt || ss| VqHd | vrz| VqHd S) aBGet the tree changes for a merge tree relative to all its parents. Args: store: An ObjectStore for looking up objects. parent_tree_ids: An iterable of the SHAs of the parent trees. tree_id: The SHA of the merge tree. rename_detector: RenameDetector object for detecting renames. Returns: Iterator over lists of TreeChange objects, one per conflicted path in the merge. Each list contains one element per parent, with the TreeChange for that path relative to that parent. An element may be None if it never existed in one parent and was deleted in two others. A path is only included in the output if it is a conflict, i.e. its SHA in the merge tree is not found in any of the parents, or in the case of deletes, if not all of the old SHAs match. csg|] }t|dqS))r])ra).0t)r]rKrirr sz*tree_changes_for_merge..cs dgSrrr) num_parentsrrs z(tree_changes_for_merge..cSs|jjSr)r!rHcrrrold_sha!sz'tree_changes_for_merge..old_shacSs|jSr)r'rorrrr`$sz+tree_changes_for_merge..change_typecSsg|]}|dur|qSrr)rjrprrrrl*sN) r4r enumerater'r r!r(rsorteditemsrfrg)rKrhrir]all_parent_changeschanges_by_pathr>parent_changeschanger(rqr`_changeshaver)rmr]rKrirtree_changes_for_merges<      r|@objc Cstt}t}d}|j}|j}|j}|j}t| D]0}| dd} || |d7}| dks4|t krL|} |t | t | 7<|d|d}q|dkr`|} |t | t | 7<|S)zCount the blocks in an object. Splits the data into blocks either on lines or <=64-byte chunks of lines. Args: obj: The object to count blocks for. Returns: A dict of block hashcode -> total bytes occurring. rrbig )rintrwriteseektruncategetvaluer from_iterable as_raw_chunksto_bytes _BLOCK_SIZEhashr4) r~ block_countsblockn block_write block_seekblock_truncateblock_getvaluerpcbrd last_blockrrr _count_blocks:s,  rcCsPt|t|kr ||}}d}|D]\}}||}|r%|t||7}q|S)aZCount the number of common bytes in two block count dicts. Args: blocks1: The first dict of block hashcode -> total bytes. blocks2: The second dict of block hashcode -> total bytes. Returns: The number of bytes in common between blocks1 and blocks2. This is only approximate due to possible hash collisions. r)r4rtgetmin)blocks1blocks2scorercount1count2rrr _common_bytes_s  rcCs|duri}|j|vrt|||j<|j|vrt|||j<t||j||j}t||}|s6tStt|t|S)aCompute a similarity score for two objects. Args: obj1: The first object to score. obj2: The second object to score. block_cache: An optional dict of SHA to block counts to cache results between calls. Returns: The similarity score between the two objects, defined as the number of bytes in common between the two objects divided by the maximum size, scaled to the range 0-100. N)idrrmax raw_length _MAX_SCORErfloat)obj1obj2 block_cache common_bytesmax_sizerrr_similarity_scoreus  rcCs0|jj}|jj}|dur|}|dur|}||fSr)r!r(r)r0path1path2rrr_tree_change_keysrc@seZdZUdZeeed<eeed<eeed<eeeefed<e e e df d'd d Z d'd d Z d dZd'ddZd'ddZd'ddZd'ddZddZddZd'ddZd'ddZd'dd Zd!d"Zd'd#d$Z d(d%d&ZdS))RenameDetectorz7Object for handling rename detection between two trees._adds_deletes_changes _candidatesFr*NcCs(||_||_||_||_||_d|_dS)aInitialize the rename detector. Args: store: An ObjectStore for looking up objects. rename_threshold: The threshold similarity score for considering an add/delete pair to be a rename/copy; see _similarity_score. max_files: The maximum number of adds and deletes to consider, or None for no limit. The detector is guaranteed to compare no more than max_files ** 2 add/delete pairs. This limit is provided because rename detection can be quadratic in the project size. If the limit is exceeded, no content rename detection is attempted. rewrite_threshold: The threshold similarity score below which a modify should be considered a delete/add, or None to not break modifies; see _similarity_score. find_copies_harder: If True, consider unmodified files when detecting copies. FN)_store_rename_threshold_rewrite_threshold _max_files_find_copies_harder_want_unchanged)selfrKrename_threshold max_filesrewrite_thresholdfind_copies_harderrrr__init__s  zRenameDetector.__init__cCsg|_g|_g|_dSr)rrrrrrr_resets zRenameDetector._resetcCsT|jdus|jtks|jj|jjkrdS|j|jj}|j|jj}t|||jkSr@)rr'r\r!rHrrr)rrxold_objnew_objrrr _should_splits  zRenameDetector._should_splitcCs|jtkr |j|dS|jtkr|j|dS||r5|jt|j |jt |j dS|j r=|jt ksB|jtkrJ|j|dS|j|dSr)r'rrr-r rrrrr!rrrr[r\r)rrxrrr _add_changes     zRenameDetector._add_changecCs6|jp|j}t|j||||jdD]}||qdS)NrW)rrrar_include_treesr)rrLrMrXrxrrr_collect_changess  zRenameDetector._collect_changescs0fdd|jD|_fdd|jD|_dS)Ncg|] }|jjvr|qSrrr(rja) add_pathsrrrlz)RenameDetector._prune..crrr!r(rjd) delete_pathsrrrlr)rr)rrrr)rrr_pruneszRenameDetector._prunecCsZtt}|jD] }||jj|jqtt}|jD]}|jtk}||j j|j |fqt }t }| D]k\}} ||} t | | D]1\\} }} t | jt | jkrYqF|ra|| j|| j|rktplt} |jt| | | qFt| t| }| dd} |dkr| | dD]} || j|jtt| | qq9|||dS)Nr)rlistrrrHr-rr'r r!setrtziprBrZrArr( CHANGE_RENAME CHANGE_COPYrrr4r)radd_mapr delete_mapr is_deleterrrH sha_deletessha_addsr!rnew_typenum_extra_addsrrr_find_exact_renamess6        z"RenameDetector._find_exact_renamescCst|jt|j|jdkS)N)r4rrrrrrr_should_find_content_renamessz+RenameDetector._should_find_content_renamescCs*|r |jj|jjkr tS|jtkrtStSr)r!r(rr\r'r rr)r check_pathsrrrrr _rename_types  zRenameDetector._rename_typec Csg}|_|s dSi}|jdu}|jD]W}t|jjrq|jj}|j|}t |||<|j D];}t |jjt |j jkrAq0|j|j j}t|||d} | |jkrk||||} t| |j|j } || | fq0qdS)N)r)rrrrr r!rArHrrrrBrZrrrrr-) r candidatesrrrrqrrrrrrrrr_find_content_rename_candidates&s.        z.RenameDetector._find_content_rename_candidatescCs|jt}t}|jD]4\}}|jj}||vrq|jj}|j}||vr.tt|j|j}|tkr7| || ||j |q| ||dSr) rsortrrr(r!r'rrrrr-r)rrrryrxnew_pathold_path orig_typerrr_choose_content_renamesCs   z&RenameDetector._choose_content_renamescs|jdurdSidd|jD}|jD]'}|jj}||}|dur;t|jj t|jj kr;t t |j|j|<qfdd|jD|_fdd|jD|_|j 7_ dS)NcSsi|]}|jj|qSrrrrrr `sz1RenameDetector._join_modifies..crrrrmodifiesrrrlirz1RenameDetector._join_modifies..crrrrrrrrljr)rrrrr(rrBrZr!rArr\rvalues)rrrr(rrrr_join_modifies[s   zRenameDetector._join_modifiescCs8g}||j||j||j|jtd|S)N)rc)rIrrrrr)rr/rrr_sorted_changesms     zRenameDetector._sorted_changescCs |jrdSdd|jD|_dS)NcSsg|] }|jtkr|qSr)r'r[rrrrrlxsz3RenameDetector._prune_unchanged..)rrrrrr_prune_unchangeduszRenameDetector._prune_unchangedcCsP|||_||_||||||||| S)zAIterate TreeChanges between two tree SHAs, with rename detection.) rrrrrrrrrr)rrLrMrXrUrrrrYzs z#RenameDetector.changes_with_renames)r*N)FF)r"r#r$r%rr__annotations__tuplerRENAME_THRESHOLD MAX_FILESREWRITE_THRESHOLDrrrrrrrrrrrrrrrYrrrrrs8       !   r)rrDr?)F)FNFFr):r%rB collectionsrrior itertoolsrtypingr object_storerobjectsr r r r r rr\r rrr[RENAME_CHANGE_TYPESrrrrrrbytesrr1rr?rDrTrVraboolrfrgr|rdictrrrrrr _is_tree_py_merge_entries_py_count_blocks_pydulwich._diff_tree ImportErrorrrrrs        + %  E B%  p