/h!SrSSKrSSKJr SSKJr \R"S5r "S S 5r S r S r \ 4S jr\ 4SjrSrSrg!\a SrSrSrNFf=f)z A port of the Gale-Church Aligner. Gale & Church (1993), A Program for Aligning Sentences in Bilingual Corpora. https://aclweb.org/anthology/J93-1004.pdf N)logsf)normc[U5nSSSU--- nU[R"U*U-S- USUSUSUSUSUS US US US ------------------5-nUS :aU$SU- $)zComplementary error function.?gś??g5?g`yg?gƸ?gꪂIǿg#v?g9)gS?gޅ1Ogv(?gg@)absmathexp)xztrs R/var/www/auris/envauris/lib/python3.13/site-packages/nltk/translate/gale_church.pyerfccrs F S1W   BF "' *"#$/&''1Aq:~9U4V'V'X%X#"!"      < 8H7NcRSS[U[R"S5- 5-- $)u>Return the area under the normal distribution from M{-∞..x}.rr)rr sqrtr s rnorm_cdfr@s$3q499Q</0000rc~[R"S[U5- 5$![a [ S5s$f=f)Nr-inf)r logr ValueErrorfloatrs r norm_logsfrDs7 !88A O, , !=  !s !$<<rc.\rSrSrSSSSSSS.rSrSrS rg ) LanguageIndependentNgׁsF?g{Gz?gbX9ȶ?gI +?))rr)rr)rr)rr)rr)rrrg333333@N)__name__ __module__ __qualname____firstlineno__PRIORSAVERAGE_CHARACTERSVARIANCE_CHARACTERS__static_attributes__r rrrrNs+  Frrc/n[U5[U54nUS:wa[SU55(aXupV[U5H:n[U5H(nUR USU- S- USU- S- 45 M* M< USU- USU- 4nUS:wa[SU55(aMUSSS2$![a USS- USS- 4nMf=f)a Traverse the alignment cost from the tracebacks and retrieves appropriate sentence pairs. :param backlinks: A dictionary where the key is the alignment points and value is the cost (referencing the LanguageIndependent.PRIORS) :type backlinks: dict :param source_sents_lens: A list of target sentences' lengths :type source_sents_lens: list(int) :param target_sents_lens: A list of target sentences' lengths :type target_sents_lens: list(int) )rrc3*# UH oS:v M g7f)rNr ).0ps r trace..ns$>X!VXsrrN)lenall TypeErrorrangeappend) backlinkssource_sents_lenstarget_sents_lenslinkspositionsr ijs rtracer=`s E%&,=(>?H f $>X$>!>!> &DAqA1X hqkAo18A;?Q3FGHQK!OXa[1_5 f $>X$>!>!> 2;   a!q9H  sB==CCc^^^^[UU4Sj[US555n[UU4Sj[US555nXgUR- -S- nXeR-U- [R"XR -5- n [[[U 55-[R"URU5-*$![ a [S5s$f=f)a,Returns the log probability of the two sentences C{source_sents[i]}, C{target_sents[j]} being aligned with a specific C{alignment}. @param i: The offset of the source sentence. @param j: The offset of the target sentence. @param source_sents: The list of source sentence lengths. @param target_sents: The list of target sentence lengths. @param alignment: The alignment type, a tuple of two integers. @param params: The sentence alignment parameters. @returns: The log probability of a specific alignment between the two sentences, given the parameters. c3:># UHnTTU- S- v M g7frNr )r+offsetr; source_sentss rr-!align_log_prob.. M9Lvl1v:>*9Lrc3:># UHnTTU- S- v M g7fr@r )r+rAr< target_sentss rr-rCrDrErrr) sumr3r&r rr'ZeroDivisionErrorrLOG2rrrr%) r;r<rBrG alignmentparamsl_sl_tmdeltas ```` ralign_log_probrQ|s  My|9L M MC My|9L M MC222 2a 700036$)) ** *;   Js5z* *TXXfmmI6N-O O PP V}s ACC*)C*c R[URR55n//n0n[[ U5S-5Hn[[ U5S-5Hn[ S5nSn UHJn SU S- n XzS- n U [ U5*:dU S:aM*XKU [ XgXX5-n X:dMFU nU n ML U[ S5:XaSnXXg4'USRU5 M [ U5S:aURS5 UR/5 M [XPU5$)amReturn the sentence alignment of two text blocks (usually paragraphs). >>> align_blocks([5,5,5], [7,7,7]) [(0, 0), (1, 1), (2, 2)] >>> align_blocks([10,5,5], [12,20]) [(0, 0), (1, 1), (2, 1)] >>> align_blocks([12,20], [10,5,5]) [(0, 0), (1, 1), (1, 2)] >>> align_blocks([10,2,10,10,2,10], [12,3,20,3,12]) [(0, 0), (1, 1), (2, 2), (3, 2), (4, 3), (5, 4)] @param source_sents_lens: The list of source sentence lengths. @param target_sents_lens: The list of target sentence lengths. @param params: the sentence alignment parameters. @return: The sentence alignments, a list of index pairs. rinfNr/rr) listr%keysr3r0rrQr4popr=)r6r7rLalignment_typesDr5r;r<min_dist min_alignaprev_iprev_jr,s r align_blocksr^s5$6==--/0O AI 3()A- .s,-12AU|HI$adqTSVG#vzIf%+)< H !I%5<' )qf  bELL "'3* q6A: EE!H  1/4 /@ AArc [U5[U5:wa [S5e[X5VVs/sHup4[X4U5PM snn$s snnf)aCreates the sentence alignment of two texts. Texts can consist of several blocks. Block boundaries cannot be crossed by sentence alignment links. Each block consists of a list that contains the lengths (in characters) of the sentences in this block. @param source_blocks: The list of blocks in the source text. @param target_blocks: The list of blocks in the target text. @param params: the sentence alignment parameters. @returns: A list of sentence alignment lists z>Source and target texts do not have the same number of blocks.)r0rzipr^) source_blocks target_blocksrL source_block target_blocks r align_textsres\ =S// L  +.m*K *K &L \8*K  sAc#R^^# UU4SjnU"TR55v M7f)zSplits an iterator C{it} at values of C{split_value}. Each instance of C{split_value} is swallowed. The iterator produces subiterators which need to be consumed fully before the next subiterator can be used. c3X># UnUT:waUv TR5nUT:waMgg7fNnext)firstvit split_values r_chunk_iterator!split_at.._chunk_iterators- ;G A;s#**ri)rmrnros`` rsplit_atrqs& bggi(( s#'c [X5VVs/sH/n[X15Vs/sHn[SU55PM snPM1 snn$s snfs snnf)zParses a stream of tokens and splits it into sentences (using C{soft_delimiter} tokens) and blocks (using C{hard_delimiter} tokens) for use with the L{align_texts} function. c38# UHn[U5v M g7frh)r0)r+tokens rr-%parse_token_stream..s4 uE s)rqrH)streamsoft_delimiterhard_delimiterblock_it sentence_its rparse_token_streamr{s_!8   9H (A A  4 4 4A 9    sAA A A)__doc__r rrr scipy.stats ImportErrorrrrrJrr=rQr^rerqr{r rrrs 4!( j xx{$8Q8?R3Bl6I:)$ M1!%N1![1!s A AA