From 0750c64f48a41eee35a3e185298b4609bb19dad0 Mon Sep 17 00:00:00 2001 From: voje Date: Mon, 11 Mar 2019 00:51:05 +0100 Subject: [PATCH] weird bug: Parser.py 175 --- src/pkg/corpusparser/corpusparser/Parser.py | 26 ++++++++++-------- .../__pycache__/Parser.cpython-35.pyc | Bin 0 -> 5389 bytes .../__pycache__/Sentence.cpython-35.pyc | Bin 0 -> 448 bytes .../__pycache__/__init__.cpython-35.pyc | Bin 0 -> 249 bytes 4 files changed, 14 insertions(+), 12 deletions(-) create mode 100644 src/pkg/corpusparser/corpusparser/__pycache__/Parser.cpython-35.pyc create mode 100644 src/pkg/corpusparser/corpusparser/__pycache__/Sentence.cpython-35.pyc create mode 100644 src/pkg/corpusparser/corpusparser/__pycache__/__init__.cpython-35.pyc diff --git a/src/pkg/corpusparser/corpusparser/Parser.py b/src/pkg/corpusparser/corpusparser/Parser.py index 9fb0e91..fb8b408 100644 --- a/src/pkg/corpusparser/corpusparser/Parser.py +++ b/src/pkg/corpusparser/corpusparser/Parser.py @@ -64,16 +64,20 @@ class Parser(): }] return res_links - def parse_srl_links(self, sent_el, xml_file=None): + def parse_srl_links(self, sent_el, sent_srl_links): if self.corpus == "kres": - return self.parse_srl_links_kres(sent_el, xml_file) + return self.parse_srl_links_kres(sent_el, sent_srl_links) else: return self.parse_any_links_ssj(sent_el, "SRL") - def parse_srl_links_kres(self, sent_el, sent_srl_dict): + def parse_srl_links_kres(self, sent_el, sent_srl_links): + print("HA") + if len(sent_srl_links) == 0: + print("HI") + return [] print(sent_srl_dict) # find the correspointing json file with srl links - return "TODO" + return [] def parse(self): if self.corpus == "kres": @@ -158,20 +162,18 @@ class Parser(): sentence_id = "{}.{}.{}".format(f_id, p_id, s_id) # make a generator instead of holding the whole corpus in memory - # TODO -- match ids - print("---") - print(sorted(srl_dict.keys(), key=lambda x: x.split(".")[1])[:100]) - print(sentence_id) - print(srl_dict.get(str(sentence_id))) - print("---") if sentence_id in res_dict: raise KeyError("duplicated id: {}".format(sentence_id)) + jos_links = self.parse_jos_links(s) + srl_links = srl_dict.get(sentence_id) if self.corpus == "kres" else None + srl_links_fixed = self.parse_srl_links(s, srl_links) + print(srl_links) res_dict[sentence_id] = { "sid": sentence_id, "text": sentence_text, "tokens": sentence_tokens, - "jos_links": self.parse_jos_links(s), - "srl_links": self.parse_srl_links(s, srl_dict[sentence_id]), + "jos_links": "BBBB", + "srl_links": "AAAAA", } print(res_dict[sentence_id]) diff --git a/src/pkg/corpusparser/corpusparser/__pycache__/Parser.cpython-35.pyc b/src/pkg/corpusparser/corpusparser/__pycache__/Parser.cpython-35.pyc new file mode 100644 index 0000000000000000000000000000000000000000..e438b679e512adfece77441901df5aaacf36d388 GIT binary patch literal 5389 zcmb7IOOqSb6+XAS)q0F%&D%46VA&WCGO>mt5RBuvFg6epG9ie{Pz_E;R<{OeS}o1( z7RX|>!6C4tvPfl-tg=fLe;~Uovdk~&ZC3mRZ<6nvmNX;9EYdT5bsy*4d*0{V-Yk_0 zU;g#WkE8QM|E5!qiT>+&BNvT_e?7 zHg&V)WJ$g4Va}%C0o|s@201zMOsZG2-{BCdsw7wU!`Kg-KKj;sjrfy2bTWRdeZR>d z)5k#Pb-d9r8lRXb(Bv3QCMd%JAPZZ2mh?f@^kAkcOI}XqZSwNu6{L^JCGv{W2U#WZ z&PX2sW%8D#Um$OVyjAG~cnzelC-!>{9r?P+661$|`MrlX`V*RC(4^?lApHu(7=lWJ zwjV13@vfRqnX@T_!kQpig0w${I6*QgEK)37VVf_oQ@WWjd64$OTb3q$VHm6)7;+}q zBamL$ORPifM_Pf%@3?WyDC&%^-_-|$E)-E|_H=&`RiaONgTSji^ea19->LL;Wrq=W zYKi(RQO!iv9i!i@<~8%3Eb*G#>II&!ld=pV9ZV;3*urhK13xMJx)BWgH?{8R#7>V& z?0xrxyKmPM``+ZYF27YXu_8Zc=`tUXZHK%;^f%HQ7(aP=x37C0zZvgFy1CmwJlIWl z>x*LM2dT1Z{YOd8b=zS(cHJfH5v`*kqo~%@rYfpUqiE#uTU4X+1Y-)_WZUD1e`k7r z5d)~RBaXtVz92)<3{+I-H3(m<6NXq58N=|yhP4i6)j zMVPFmvyJf4WEOI)8hQ;IB-sesa{WNWkv5w=UtZYh93~?^l2loh%+cnAw*{~niy1%` z@QNvaiw+n_Sp-jGgJSS!5c)9aLn3{HVi>o{Gcd{nqOnOsEf#Ol_WcJf8e4P>x6Dv% z(y>LIsSS6;ba|(O_yKHpvYeIubEgpUJadAuBnWMjjr~;|cyx#MaYnsb+#BU;ySpMo zodxxym3xhFC$6;Gp;wXVn%I6~wREqWs9It*T7xh#;+|uAe*e4w;L#OeR_!FqSdAb^ z%)k$m>^r|q4cBakabh0$agvGpK|8KyL?xOs$R|P zH8}?G!=`QFt>cZJMFUmBf*)+tSS*@tfF^q1{)0hBHt)?cez!pTmddX|y}XDhG?Wp&?%vZS8i@Yc_)D4mwlZC#o_>H=DQ6 zeH)z#-7hiS9C~42MB9^SygTtn80?pbts(4En3^(VrN*IR;R%^YU&WU2x$F4RFL1-* z=fvOi4={Wg?}Qg%hy={kORd-+#*P_8@d92l@%RO1c_RxAWiF@%3z&zTrJfvs^LW_` zqQ9V-^H-C;B5H}Vg5}?1)fCmk6t>})kkvRt!zMf4{Rbb>*q(+kn`0Mz7G{F~F`4MC)n(7Q?L;R?Z@H;3~(;qKF$78Be7E> zMc9WyJcA}N8)4&#x|RCFB__tw?BtqLg;19oNA4tE=$CkD2aS^vQuXsZQRN8}2MEz% zO~5$7>uoeY!aIu`7ZEo~Y73F0pf0E_V|4EOxtW>GT;O0|gs-Pzo-^5{sTrif9?6TB zzc-ng_4nUh$Yh-TQ_*uK6QTjZ`c1>+8A)F=s73FXWU<-$J!Y8QoU_=nv5>`PU~}xT zZUv7ujYxnH08>_T2@JemmoUOABpf~guWdvq zsbEixb08rO<$x5`P!uBDHi`gd#^e$iF%Gj_EeLPtxd1`kf$CV|**6zB=*3y;SPJ4C0=@Lay*So)H%b$4z3!q2@V_QBqU=8@G`3_SJg4*v6`o_Oz3x(`KH3~sP7@5 z0uBFV9Ot3%e;Q+iUyy=3OIaX_H2l`!8Q?7Q%>4&{HpU3CgKic1&AqIHAExO$PKY+hfH4L4Bwp|{GHG7lgd6mK#vc=XW00UP90D*y7c2dkVbGLzc=p!KxycWzt%6m5%?rdzJN>^K-g!#-IFao2l(naj zet}769;ZZ4^X9@?TXGgo2R9|*9i-rY-@8a1kY1!?7!-62`@)9!F9-(m$T{+!5tt3; z2mgG3gf`BzQZXFk=+hSWm5CA&`oShxO{=6aLgquJUl5XRxpr z`frVLpO0(uKU(nyxCk^GvF}yd-mS{#V_d7-o@2+oLqEiAV0N){tT*r^`B{W_GI#kI zy>jFKeJXG6-PaW+>M2e2ne<|5g^jK+Rfp!BBe!*D>9cnHi5m@Ct@bdndVO4OERkv^ z=rz13v9#at65I2eJ19sl=}^?>7=GYn{D481W@|8wH<)5hQBHZLN6+McS&m zV5}NzMp>O#8^)G_c~vyZhHaKq*#rc?fVRywhE>b>E1|%%aY@Vr_OiML{0)4$NM~() zy;wC$rlmH_qS^q&RW2>CZ~C`vo}5IYLjPGOJ0bki6xQb{A8Y>s-;9I>h^ zgLo31&+nHv%ZS;rR8?(0LAlL6{G7#7HBX{2u~tPapC99*QL@!CS6Zm;q?bOGuQu%E z-9_2~u+9F^(N`092V$MC1)`lGuA8!5xp<2B(&nqKqQ?C~f2*mH`(sX++>e+tpC?iG T{_FJzIf4x@x)GP2ML+NhUEyBP literal 0 HcmV?d00001 diff --git a/src/pkg/corpusparser/corpusparser/__pycache__/__init__.cpython-35.pyc b/src/pkg/corpusparser/corpusparser/__pycache__/__init__.cpython-35.pyc new file mode 100644 index 0000000000000000000000000000000000000000..a365c8e295dbed9a0472980368c09666df7d3ef2 GIT binary patch literal 249 zcmWgR<>jikZ;c6LU|@I*#Bjg_WH|tFu?mn#0U}0*90rD5MusRx21XE{i6MuHA(xpU ziW$gfW(d|~c?nd>pvicPEg-R|IJF4K;s{R7D@n~uPW97di4soEFDfW4E&xmFLDUq1 ztcemuk%8$cVg|~sWGG?*QefhjnSMc0epYI7iGFcWvVK8!x<0Z-R8D++W?p7Ve7s&k X