U -e*@spddlmZddlmZmZmZddlmZddlm Z ddl m Z m Z ddl mZddl mZddl mZdd l mZd d d d d d dddddZd+dd d dddddZd d d d d d dddddZd d d d d d dddddZd,dd d dddddZd d d d d d ddddd Zd-dd d dddd!d"Zd d#d d d d$d%d&d'Zd d#d d d d(d%d)d*Zd S).) annotations)CallableHashableSequence)conv_sequences)is_none)EditopsOpcodes)_block_similarity)editops)opcodes) similarityN) processor score_cutoffzSequence[Hashable]z(Callable[..., Sequence[Hashable]] | Nonez int | Noneint)s1s2rrreturncCsh|dk r||}||}t||\}}t|t|}t||}|d|}|dks\||kr`|S|dS)a Calculates the minimum number of insertions and deletions required to change one sequence into the other. This is equivalent to the Levenshtein distance with a substitution weight of 2. Parameters ---------- s1 : Sequence[Hashable] First string to compare. s2 : Sequence[Hashable] Second string to compare. processor: callable, optional Optional callable that is used to preprocess the strings before comparing them. Default is None, which deactivates this behaviour. score_cutoff : int, optional Maximum distance between s1 and s2, that is considered as a result. If the distance is bigger than score_cutoff, score_cutoff + 1 is returned instead. Default is None, which deactivates this behaviour. Returns ------- distance : int distance between s1 and s2 Examples -------- Find the Indel distance between two strings: >>> from rapidfuzz.distance import Indel >>> Indel.distance("lewenstein", "levenshtein") 3 Setting a maximum distance allows the implementation to select a more efficient implementation: >>> Indel.distance("lewenstein", "levenshtein", score_cutoff=1) 2 N)rlenlcs_seq_similarity)rrrrmaximumlcs_simdistr\/var/www/html/Darija-Ai-Train/env/lib/python3.8/site-packages/rapidfuzz/distance/Indel_py.pydistances/  rzdict[Hashable, int])blockrrrrcCsDt|t|}t|||}|d|}|dks8||kr<|S|dS)Nrr)rlcs_seq_block_similarity)rrrrrrrrrr_block_distanceKs  r cCs`|dk r||}||}t||\}}t|t|}t||}||}|dksX||kr\|SdS)a Calculates the Indel similarity in the range [max, 0]. This is calculated as ``(len1 + len2) - distance``. Parameters ---------- s1 : Sequence[Hashable] First string to compare. s2 : Sequence[Hashable] Second string to compare. processor: callable, optional Optional callable that is used to preprocess the strings before comparing them. Default is None, which deactivates this behaviour. score_cutoff : int, optional Maximum distance between s1 and s2, that is considered as a result. If the similarity is smaller than score_cutoff, 0 is returned instead. Default is None, which deactivates this behaviour. Returns ------- similarity : int similarity between s1 and s2 Nr)rrr)rrrrrrsimrrrr Ws  r z float | NonefloatcCs|t|st|rdS|dk r,||}||}t||\}}t|t|}t||}|r`||nd}|dkst||krx|SdS)a8 Calculates a normalized levenshtein similarity in the range [1, 0]. This is calculated as ``distance / (len1 + len2)``. Parameters ---------- s1 : Sequence[Hashable] First string to compare. s2 : Sequence[Hashable] Second string to compare. processor: callable, optional Optional callable that is used to preprocess the strings before comparing them. Default is None, which deactivates this behaviour. score_cutoff : float, optional Optional argument for a score threshold as a float between 0 and 1.0. For norm_dist > score_cutoff 1.0 is returned instead. Default is 1.0, which deactivates this behaviour. Returns ------- norm_dist : float normalized distance between s1 and s2 as a float between 0 and 1.0 ?Nrr)rrrr)rrrrrr norm_distrrrnormalized_distances r%cCsDt|t|}t|||}|r(||nd}|dks<||kr@|SdS)Nrr)rr )rrrrrrr$rrr_block_normalized_distances r&cCsdt|st|rdS|dk r,||}||}t||\}}t||}d|}|dks\||kr`|SdS)a Calculates a normalized indel similarity in the range [0, 1]. This is calculated as ``1 - normalized_distance`` Parameters ---------- s1 : Sequence[Hashable] First string to compare. s2 : Sequence[Hashable] Second string to compare. processor: callable, optional Optional callable that is used to preprocess the strings before comparing them. Default is None, which deactivates this behaviour. score_cutoff : float, optional Optional argument for a score threshold as a float between 0 and 1.0. For norm_sim < score_cutoff 0 is returned instead. Default is 0, which deactivates this behaviour. Returns ------- norm_sim : float normalized similarity between s1 and s2 as a float between 0 and 1.0 Examples -------- Find the normalized Indel similarity between two strings: >>> from rapidfuzz.distance import Indel >>> Indel.normalized_similarity("lewenstein", "levenshtein") 0.85714285714285 Setting a score_cutoff allows the implementation to select a more efficient implementation: >>> Indel.normalized_similarity("lewenstein", "levenshtein", score_cutoff=0.9) 0.0 When a different processor is used s1 and s2 do not have to be strings >>> Indel.normalized_similarity(["lewenstein"], ["levenshtein"], processor=lambda s: s[0]) 0.8571428571428572 gNr#r)rrr%)rrrrr$norm_simrrrnormalized_similaritys2 r(cCs,t|||}d|}|dks$||kr(|SdS)Nr#r)r&)rrrrr$r'rrr_block_normalized_similaritys r)rr)rrrrcCst|||dS)ua Return Editops describing how to turn s1 into s2. Parameters ---------- s1 : Sequence[Hashable] First string to compare. s2 : Sequence[Hashable] Second string to compare. processor: callable, optional Optional callable that is used to preprocess the strings before comparing them. Default is None, which deactivates this behaviour. Returns ------- editops : Editops edit operations required to turn s1 into s2 Notes ----- The alignment is calculated using an algorithm of Heikki Hyyrö, which is described [6]_. It has a time complexity and memory usage of ``O([N/64] * M)``. References ---------- .. [6] Hyyrö, Heikki. "A Note on Bit-Parallel Alignment Computation." Stringology (2004). Examples -------- >>> from rapidfuzz.distance import Indel >>> for tag, src_pos, dest_pos in Indel.editops("qabxcd", "abycdf"): ... print(("%7s s1[%d] s2[%d]" % (tag, src_pos, dest_pos))) delete s1[0] s2[0] delete s1[3] s2[2] insert s1[4] s2[2] insert s1[6] s2[5] r*)lcs_seq_editopsrrrrrrr s,r r cCst|||dS)u Return Opcodes describing how to turn s1 into s2. Parameters ---------- s1 : Sequence[Hashable] First string to compare. s2 : Sequence[Hashable] Second string to compare. processor: callable, optional Optional callable that is used to preprocess the strings before comparing them. Default is None, which deactivates this behaviour. Returns ------- opcodes : Opcodes edit operations required to turn s1 into s2 Notes ----- The alignment is calculated using an algorithm of Heikki Hyyrö, which is described [7]_. It has a time complexity and memory usage of ``O([N/64] * M)``. References ---------- .. [7] Hyyrö, Heikki. "A Note on Bit-Parallel Alignment Computation." Stringology (2004). Examples -------- >>> from rapidfuzz.distance import Indel >>> a = "qabxcd" >>> b = "abycdf" >>> for tag, i1, i2, j1, j2 in Indel.opcodes(a, b): ... print(("%7s a[%d:%d] (%s) b[%d:%d] (%s)" % ... (tag, i1, i2, a[i1:i2], j1, j2, b[j1:j2]))) delete a[0:1] (q) b[0:0] () equal a[1:3] (ab) b[0:2] (ab) delete a[3:4] (x) b[2:2] () insert a[4:4] () b[2:3] (y) equal a[4:6] (cd) b[3:5] (cd) insert a[6:6] () b[5:6] (f) r*)lcs_seq_opcodesr,rrrr 4s2r )N)N)N) __future__rtypingrrrZrapidfuzz._common_pyrZrapidfuzz._utilsrZ!rapidfuzz.distance._initialize_pyrr Zrapidfuzz.distance.LCSseq_pyr rr r+r r-r rrr r%r&r(r)rrrrs<       >/1C3