udapted scripts
This commit is contained in:
parent
0c2ed6944f
commit
90c6fa32c1
|
@ -1,183 +0,0 @@
|
|||
OGNTsort BW-mm
|
||||
001339 V-I|AAI-3S
|
||||
001446 N-N|VSF
|
||||
001449 N-N|VSF
|
||||
001456 N-N|VSF-L
|
||||
002311 D-GPN|M
|
||||
002313 T-GSM|N
|
||||
002314 A-GSM|N
|
||||
002332 T-DSN|M
|
||||
002729 T-GSM|N
|
||||
---- followings to be checked ------
|
||||
005737 anamsc/anansc
|
||||
007490 V-I|AAI-3S
|
||||
010230 V-I|AAI-3S
|
||||
010472 acgmsn/acgnsn
|
||||
010473 dgmp/dgnp
|
||||
010474 angmpn/angnpn
|
||||
011277 V-I|AAI-3S
|
||||
012521 V-I|AAI-3S
|
||||
013287 aigmpn/aignpn
|
||||
013408 V-I|AAI-3S
|
||||
013980 angmpn/angnpn
|
||||
014321 nnfpc/nnmpc
|
||||
014722 vipa2p/vdpa2p
|
||||
014870 vipa2p/vdpa2p
|
||||
015295 V-I|AAI-3S
|
||||
015338 V-I|AAI-3S
|
||||
015856 nafsc/namsc
|
||||
016276 V-I|AAI-3S
|
||||
017996 V-I|AAI-3S
|
||||
021553 rqnfs/aqnfsn
|
||||
023937 V-I|AAI-3S
|
||||
024376 V-I|AAI-3S
|
||||
024873 V-I|AAI-3S
|
||||
025028 V-I|AAI-3S
|
||||
026126 b/anamsn
|
||||
026430 V-I|AAI-3S
|
||||
027324 vipa2p/vdpa2p
|
||||
027922 V-I|AAI-3S
|
||||
030929 V-I|AAI-3S
|
||||
031443 atdfsn/rtdfs
|
||||
032611 rpdms/rpdns
|
||||
032865 nnmsc/nnnsc
|
||||
032873 rqnms/aqnmsn
|
||||
033194 nnmsc/nnnsc
|
||||
035188 anamsc/anansc
|
||||
035375 nafsc/namsc
|
||||
035425 rqnfs/aqnfsn
|
||||
035769 rqnfs/aqnfsn
|
||||
037954 atdfsn/rpdfs
|
||||
038204 atdfsn/rtdfs
|
||||
039840 atdfsn/rtdfs
|
||||
040132 aianpn/ainnpn
|
||||
040274 vipa2p/vdpa2p
|
||||
040325 aqnmsn/rqnms
|
||||
040665 atdmsn/rtdms
|
||||
040669 atdmsn/rtdms
|
||||
041216 atdfsn/rtdfs
|
||||
042213 ndfsc/ndmsc
|
||||
043542 nansc/nnnsc
|
||||
043544 nansc/nnnsc
|
||||
044085 namsc/nafsc
|
||||
044497 pd/pg
|
||||
044499 ndfsp/ngfsp
|
||||
045395 atdfsn/rtdfs
|
||||
045957 nnfpc/nnmpc
|
||||
046258 vipa2p/vdpa2p
|
||||
047663 atdfsn/rtdfs
|
||||
048549 rqnmp/aqnmpn
|
||||
048842 atdfsn/rtdfs
|
||||
049236 vppmams/vppmnns
|
||||
050688 vsaa3s/vspa3s
|
||||
050951 aigmpn/aignpn
|
||||
050973 aigmpn/aignpn
|
||||
052654 vipa2p/vdpa2p
|
||||
053457 vsaa1s/vifa1s
|
||||
053782 b&rpn-s/cc&rpn-s
|
||||
055128 vsaa1s/vspa1s
|
||||
055267 dgmp/dgnp
|
||||
055272 dgmp/dgnp
|
||||
058604 vipa2p/vdpa2p
|
||||
059844 vipa2p/vdpa2p
|
||||
059851 vipa2p/vdpa2p
|
||||
060735 vipa2p/vdpa2p
|
||||
060772 vipa2p/vdpa2p
|
||||
061790 T-GSM|N
|
||||
061797 T-GSM|N
|
||||
063351 ndfsc/ndmsc
|
||||
066321 rddms/rddns
|
||||
068577 nnfsc/nnmsc
|
||||
071281 rqnfs/aqnfsn
|
||||
071398 V-I|AAI-3S
|
||||
071563 aigmpn/aignpn
|
||||
074732 vnpm/vnpp
|
||||
075264 atdfsn/rtdfs
|
||||
075568 V-I|AAI-3S
|
||||
075573 b/andfsn
|
||||
076165 rpgmp/rpgnp
|
||||
076811 b/andfsn
|
||||
077935 b/andfsn
|
||||
079291 atdfsn/rtdfs
|
||||
079686 V-I|AAI-3S
|
||||
081192 vipa2p/vdpa2p
|
||||
084217 rqnfs/aqnfsn
|
||||
085144 T-GSM|N
|
||||
085145 A-GSM|N
|
||||
085394 acgmsn/acgnsn
|
||||
085404 acgmsn/acgnsn
|
||||
086511 atgnsn/rpgms
|
||||
086768 aianpn/ainnpn
|
||||
086893 nnfsc/nnmsc
|
||||
087040 aigmpn/aignpn
|
||||
087426 nnfsp/nnnpp
|
||||
087672 atnmsn/rtnms
|
||||
088057 vifa1s/vsaa1s
|
||||
088062 vifa1s/vsaa1s
|
||||
088073 rqnfs/aqnfsn
|
||||
088635 ddmp/ddnp
|
||||
088636 andmpn/andnpn
|
||||
090732 vipa2p/vdpa2p
|
||||
091068 andmpn/andnpn
|
||||
091152 nnmsc/nnnsc
|
||||
092950 annfsn/annmsn
|
||||
094554 vipa2p/vdpa2p
|
||||
095354 nnnsc/nansc
|
||||
095356 nnnsc/nansc
|
||||
095378 rdgnp/rdgfp
|
||||
099999 rdans/rdnns
|
||||
100496 vipm2p/vdpm2p
|
||||
100901 ndfsc/ndmsc
|
||||
101338 danp/dnnp
|
||||
102458 vipa2p/vdpa2p
|
||||
103687 vsaa3s/vspa3s
|
||||
104160 rqnfs/aqnfsn
|
||||
104167 rqnfs/aqnfsn
|
||||
104755 rqnfs/aqnfsn
|
||||
105014 aigmpn/aignpn
|
||||
105017 aigmpn/aignpn
|
||||
105020 aigmpn/aignpn
|
||||
105496 vdxa2p/vixa2p
|
||||
105687 aigmpn/aignpn
|
||||
108996 aidmpn/aidnpn
|
||||
109852 vipa2p/vdpa2p
|
||||
110541 rigms/rigns
|
||||
111572 T-GSM|N
|
||||
112904 rinfp/rinmp
|
||||
114554 aianpn/ainnpn
|
||||
115500 anamsn/b
|
||||
116032 aigmsn/aignsn
|
||||
116068 acgmsn/acgnsn
|
||||
117367 vipa2p/vdpa2p
|
||||
117431 T-GSM|N
|
||||
118377 ngfsc/ngmsc
|
||||
118918 nnmsc/nnnsc
|
||||
119142 rtgms/rpgms
|
||||
120005 vixa2p/vdxa2p
|
||||
120232 aidmpn/aidnpn
|
||||
120546 vipa2p/vdpa2p
|
||||
122410 rrdms/rrdns
|
||||
122411 vipm2p/vdpm2p
|
||||
122457 vipm2p/vdpm2p
|
||||
122784 vipp2p/vdpp2p
|
||||
124062 rrgnp/rrgfp
|
||||
124690 rrdms/rrdns
|
||||
124694 rddms/rddns
|
||||
125446 rpdms/rpdns
|
||||
125856 vipa2p/vdpa2p
|
||||
125884 vipa2p/vdpa2p
|
||||
126387 vipa2p/vdpa2p
|
||||
127468 nansc/nnnsc
|
||||
127470 nansc/nnnsc
|
||||
127615 rddmp/rddnp
|
||||
127690 nansc/nnnsc
|
||||
127692 nansc/nnnsc
|
||||
128421 nafsp/nansp
|
||||
128491 ndmsc/ndnsc
|
||||
128882 ndfsp/ndnsp
|
||||
130601 ndfsc/ndmsc
|
||||
131747 angmpn/angnpn
|
||||
133305 rpgms/rpgns
|
||||
133311 rpgms/rpgns
|
||||
133322 rpgms/rpgns
|
||||
133326 rpgms/rpgns
|
|
@ -1,4 +1,198 @@
|
|||
OGNTsort Friberg-mm
|
||||
OGNTsort reference Greek rmac-old rmac-new
|
||||
001339 Mat 4:7 Ἔφη V-IAI-3S V-I|AAI-3S
|
||||
001446 Mat 4:15 ¬Γῆ N-NSF N-N|VSF
|
||||
001449 Mat 4:15 γῆ N-NSF N-N|VSF
|
||||
001456 Mat 4:15 ¬Γαλιλαία N-NSF-L N-N|VSF-L
|
||||
002311 Mat 5:37 τούτων D-GPN D-GPN|M
|
||||
002313 Mat 5:37 τοῦ T-GSM T-GSM|N
|
||||
002314 Mat 5:37 πονηροῦ A-GSM A-GSM|N
|
||||
002332 Mat 5:39 τῷ T-DSN T-DSN|M
|
||||
002729 Mat 6:13 τοῦ T-GSN T-GSM|N
|
||||
018408 Mar 1:5 Ἰουδαία N-NSF-L A-NSF-L
|
||||
044656 Luk 19:21 αὐστηρὸς P-NSM A-NSM
|
||||
044681 Luk 19:22 αὐστηρός P-NSM A-NSM
|
||||
|
||||
|
||||
|
||||
|
||||
---- followings to be checked ------
|
||||
005737 anamsc/anansc
|
||||
007490 V-I|AAI-3S
|
||||
010230 V-I|AAI-3S
|
||||
010472 acgmsn/acgnsn
|
||||
010473 dgmp/dgnp
|
||||
010474 angmpn/angnpn
|
||||
011277 V-I|AAI-3S
|
||||
012521 V-I|AAI-3S
|
||||
013287 aigmpn/aignpn
|
||||
013408 V-I|AAI-3S
|
||||
013980 angmpn/angnpn
|
||||
014321 nnfpc/nnmpc
|
||||
014722 vipa2p/vdpa2p
|
||||
014870 vipa2p/vdpa2p
|
||||
015295 V-I|AAI-3S
|
||||
015338 V-I|AAI-3S
|
||||
015856 nafsc/namsc
|
||||
016276 V-I|AAI-3S
|
||||
017996 V-I|AAI-3S
|
||||
021553 rqnfs/aqnfsn
|
||||
023937 V-I|AAI-3S
|
||||
024376 V-I|AAI-3S
|
||||
024873 V-I|AAI-3S
|
||||
025028 V-I|AAI-3S
|
||||
026126 b/anamsn
|
||||
026430 V-I|AAI-3S
|
||||
027324 vipa2p/vdpa2p
|
||||
027922 V-I|AAI-3S
|
||||
030929 V-I|AAI-3S
|
||||
031443 atdfsn/rtdfs
|
||||
032611 rpdms/rpdns
|
||||
032865 nnmsc/nnnsc
|
||||
032873 rqnms/aqnmsn
|
||||
033194 nnmsc/nnnsc
|
||||
035188 anamsc/anansc
|
||||
035375 nafsc/namsc
|
||||
035425 rqnfs/aqnfsn
|
||||
035769 rqnfs/aqnfsn
|
||||
037954 atdfsn/rpdfs
|
||||
038204 atdfsn/rtdfs
|
||||
039840 atdfsn/rtdfs
|
||||
040132 aianpn/ainnpn
|
||||
040274 vipa2p/vdpa2p
|
||||
040325 aqnmsn/rqnms
|
||||
040665 atdmsn/rtdms
|
||||
040669 atdmsn/rtdms
|
||||
041216 atdfsn/rtdfs
|
||||
042213 ndfsc/ndmsc
|
||||
043542 nansc/nnnsc
|
||||
043544 nansc/nnnsc
|
||||
044085 namsc/nafsc
|
||||
044497 pd/pg
|
||||
044499 ndfsp/ngfsp
|
||||
045395 atdfsn/rtdfs
|
||||
045957 nnfpc/nnmpc
|
||||
046258 vipa2p/vdpa2p
|
||||
047663 atdfsn/rtdfs
|
||||
048549 rqnmp/aqnmpn
|
||||
048842 atdfsn/rtdfs
|
||||
049236 vppmams/vppmnns
|
||||
050688 vsaa3s/vspa3s
|
||||
050951 aigmpn/aignpn
|
||||
050973 aigmpn/aignpn
|
||||
052654 vipa2p/vdpa2p
|
||||
053457 vsaa1s/vifa1s
|
||||
053782 b&rpn-s/cc&rpn-s
|
||||
055128 vsaa1s/vspa1s
|
||||
055267 dgmp/dgnp
|
||||
055272 dgmp/dgnp
|
||||
058604 vipa2p/vdpa2p
|
||||
059844 vipa2p/vdpa2p
|
||||
059851 vipa2p/vdpa2p
|
||||
060735 vipa2p/vdpa2p
|
||||
060772 vipa2p/vdpa2p
|
||||
061790 T-GSM|N
|
||||
061797 T-GSM|N
|
||||
063351 ndfsc/ndmsc
|
||||
066321 rddms/rddns
|
||||
068577 nnfsc/nnmsc
|
||||
071281 rqnfs/aqnfsn
|
||||
071398 V-I|AAI-3S
|
||||
071563 aigmpn/aignpn
|
||||
074732 vnpm/vnpp
|
||||
075264 atdfsn/rtdfs
|
||||
075568 V-I|AAI-3S
|
||||
075573 b/andfsn
|
||||
076165 rpgmp/rpgnp
|
||||
076811 b/andfsn
|
||||
077935 b/andfsn
|
||||
079291 atdfsn/rtdfs
|
||||
079686 V-I|AAI-3S
|
||||
081192 vipa2p/vdpa2p
|
||||
084217 rqnfs/aqnfsn
|
||||
085144 T-GSM|N
|
||||
085145 A-GSM|N
|
||||
085394 acgmsn/acgnsn
|
||||
085404 acgmsn/acgnsn
|
||||
086511 atgnsn/rpgms
|
||||
086768 aianpn/ainnpn
|
||||
086893 nnfsc/nnmsc
|
||||
087040 aigmpn/aignpn
|
||||
087426 nnfsp/nnnpp
|
||||
087672 atnmsn/rtnms
|
||||
088057 vifa1s/vsaa1s
|
||||
088062 vifa1s/vsaa1s
|
||||
088073 rqnfs/aqnfsn
|
||||
088635 ddmp/ddnp
|
||||
088636 andmpn/andnpn
|
||||
090732 vipa2p/vdpa2p
|
||||
091068 andmpn/andnpn
|
||||
091152 nnmsc/nnnsc
|
||||
092950 annfsn/annmsn
|
||||
094554 vipa2p/vdpa2p
|
||||
095354 nnnsc/nansc
|
||||
095356 nnnsc/nansc
|
||||
095378 rdgnp/rdgfp
|
||||
099999 rdans/rdnns
|
||||
100496 vipm2p/vdpm2p
|
||||
100901 ndfsc/ndmsc
|
||||
101338 danp/dnnp
|
||||
102458 vipa2p/vdpa2p
|
||||
103687 vsaa3s/vspa3s
|
||||
104160 rqnfs/aqnfsn
|
||||
104167 rqnfs/aqnfsn
|
||||
104755 rqnfs/aqnfsn
|
||||
105014 aigmpn/aignpn
|
||||
105017 aigmpn/aignpn
|
||||
105020 aigmpn/aignpn
|
||||
105496 vdxa2p/vixa2p
|
||||
105687 aigmpn/aignpn
|
||||
108996 aidmpn/aidnpn
|
||||
109852 vipa2p/vdpa2p
|
||||
110541 rigms/rigns
|
||||
111572 T-GSM|N
|
||||
112904 rinfp/rinmp
|
||||
114554 aianpn/ainnpn
|
||||
115500 anamsn/b
|
||||
116032 aigmsn/aignsn
|
||||
116068 acgmsn/acgnsn
|
||||
117367 vipa2p/vdpa2p
|
||||
117431 T-GSM|N
|
||||
118377 ngfsc/ngmsc
|
||||
118918 nnmsc/nnnsc
|
||||
119142 rtgms/rpgms
|
||||
120005 vixa2p/vdxa2p
|
||||
120232 aidmpn/aidnpn
|
||||
120546 vipa2p/vdpa2p
|
||||
122410 rrdms/rrdns
|
||||
122411 vipm2p/vdpm2p
|
||||
122457 vipm2p/vdpm2p
|
||||
122784 vipp2p/vdpp2p
|
||||
124062 rrgnp/rrgfp
|
||||
124690 rrdms/rrdns
|
||||
124694 rddms/rddns
|
||||
125446 rpdms/rpdns
|
||||
125856 vipa2p/vdpa2p
|
||||
125884 vipa2p/vdpa2p
|
||||
126387 vipa2p/vdpa2p
|
||||
127468 nansc/nnnsc
|
||||
127470 nansc/nnnsc
|
||||
127615 rddmp/rddnp
|
||||
127690 nansc/nnnsc
|
||||
127692 nansc/nnnsc
|
||||
128421 nafsp/nansp
|
||||
128491 ndmsc/ndnsc
|
||||
128882 ndfsp/ndnsp
|
||||
130601 ndfsc/ndmsc
|
||||
131747 angmpn/angnpn
|
||||
133305 rpgms/rpgns
|
||||
133311 rpgms/rpgns
|
||||
133322 rpgms/rpgns
|
||||
133326 rpgms/rpgns
|
||||
|
||||
|
||||
|
||||
——————————————
|
||||
OGNTsort Friberg-mm
|
||||
000460 dnms/dnms+
|
||||
000473 cc/ch
|
||||
000627 npdm3s/npdn3s
|
25
README.md
25
README.md
|
@ -4,7 +4,8 @@ This is an abridged and updated version of OpenGNT Version 3 [OGNT 3.3 Base Text
|
|||
|
||||
## Files
|
||||
- OpenGNT_version3_3.csv = source file from OpenGNT.
|
||||
- OGNTa.txt = the primary data file, abridged and updated from the source.
|
||||
- OGNTa-trimmed.txt = data trimmed from the source
|
||||
- **OGNTa.txt = the primary data file**, abridged and updated from the trimmed data.
|
||||
- OGNT-Marked.txt = adding verbal(verbs/participles/infinitives) emphasis for RUBY rendering.
|
||||
- OGNTa-Ruby.nt = converted to TheWord format for easier access.
|
||||
|
||||
|
@ -33,23 +34,33 @@ OGNT3.3 abridged to the following tab-separated columns:
|
|||
|
||||
|
||||
|
||||
## Content Updates
|
||||
- `018408 41-1:5 Ἰουδαία N-NSF-L` ⇒ `A-NSF-L`
|
||||
- `044656 42-19:21 αὐστηρὸς P-NSM` ⇒ `A-NSM`
|
||||
- `044681 42-19:22 αὐστηρός P-NSM` ⇒ `A-NSM`
|
||||
-
|
||||
## Content Changes
|
||||
- OGNTsort reference Greek: `'rmac-old` ⇒ `rmac-new`
|
||||
- 001339 Mat 4:7 Ἔφη: `V-IAI-3S` ⇒ `V-I|AAI-3S`
|
||||
- 001446 Mat 4:15 ¬Γῆ: `N-NSF` ⇒ `N-N|VSF`
|
||||
- 001449 Mat 4:15 γῆ: `N-NSF` ⇒ `N-N|VSF`
|
||||
- 001456 Mat 4:15 ¬Γαλιλαία: `N-NSF-L` ⇒ `N-N|VSF-L`
|
||||
- 002311 Mat 5:37 τούτων: `D-GPN` ⇒ `D-GPN|M`
|
||||
- 002313 Mat 5:37 τοῦ: `T-GSM` ⇒ `T-GSM|N`
|
||||
- 002314 Mat 5:37 πονηροῦ: `A-GSM` ⇒ `A-GSM|N`
|
||||
- 002332 Mat 5:39 τῷ: `T-DSN` ⇒ `T-DSN|M`
|
||||
- 002729 Mat 6:13 τοῦ: `T-GSN` ⇒ `T-GSM|N`
|
||||
- 018408 Mar 1:5 Ἰουδαία: `N-NSF-L` ⇒ `A-NSF-L`
|
||||
- 044656 Luk 19:21 αὐστηρὸς: `P-NSM` ⇒ `A-NSM`
|
||||
- 044681 Luk 19:22 αὐστηρός: `P-NSM` ⇒ `A-NSM`
|
||||
|
||||
---
|
||||
|
||||
## License :
|
||||
|
||||
<a rel="license" href="http://creativecommons.org/licenses/by-sa/4.0/"><img alt="Creative Commons Licence" style="border-width:0" src="https://i.creativecommons.org/l/by-sa/4.0/88x31.png" /></a><br /><span xmlns:dct="http://purl.org/dc/terms/" property="dct:title">OGNTa Project by Andley Chang is licensed under a <a rel="license" href="http://creativecommons.org/licenses/by-sa/4.0/">Creative Commons Attribution-ShareAlike 4.0 International License</a>.
|
||||
<br />Based on a work at <a xmlns:dct="http://purl.org/dc/terms/" href="https://github.com/eliranwong/OpenGNT" rel="dct:source">https://github.com/eliranwong/OpenGNT</a>.
|
||||
|
||||
---
|
||||
|
||||
## Attribution :
|
||||
|
||||
<a rel="license" href="http://creativecommons.org/licenses/by-sa/4.0/"><img alt="Creative Commons Licence" style="border-width:0" src="https://i.creativecommons.org/l/by-sa/4.0/88x31.png" /></a><br /><span xmlns:dct="http://purl.org/dc/terms/" property="dct:title">Open Greek New Testament Project</span> by <a xmlns:cc="http://creativecommons.org/ns#" href="https://marvel.bible" property="cc:attributionName" rel="cc:attributionURL">Eliran Wong</a> is licensed under a <a rel="license" href="http://creativecommons.org/licenses/by-sa/4.0/">Creative Commons Attribution-ShareAlike 4.0 International License</a>.<br />Based on a work at <a xmlns:dct="http://purl.org/dc/terms/" href="https://github.com/eliranwong/OpenGNT" rel="dct:source">https://github.com/eliranwong/OpenGNT</a>.
|
||||
<a rel="license" href="http://creativecommons.org/licenses/by-sa/4.0/"><img alt="Creative Commons Licence" style="border-width:0" src="https://i.creativecommons.org/l/by-sa/4.0/88x31.png" /></a><br /><span xmlns:dct="http://purl.org/dc/terms/" property="dct:title">Open Greek New Testament Project</span> by <a xmlns:cc="http://creativecommons.org/ns#" href="https://marvel.bible" property="cc:attributionName" rel="cc:attributionURL">Eliran Wong</a> is licensed under a <a rel="license" href="http://creativecommons.org/licenses/by-sa/4.0/">Creative Commons Attribution-ShareAlike 4.0 International License</a>.
|
||||
|
||||
|
||||
|
||||
|
|
|
@ -1,16 +1,16 @@
|
|||
# trim original OGNT to mininum data
|
||||
|
||||
import re
|
||||
|
||||
sourceFile = "OpenGNT_version3_3.csv"
|
||||
abridgedFile = "OGNTa.txt"
|
||||
outputFile = "OGNTa-Marked.txt"
|
||||
inputFile = "./OpenGNT_version3_3.csv"
|
||||
outputFile = "./tmp/OGNT-trimmed.txt"
|
||||
|
||||
# ---------------------------------------------------
|
||||
f = open(sourceFile,'r',encoding="utf-8")
|
||||
f = open(inputFile,'r',encoding="utf-8")
|
||||
newData = f.read()
|
||||
f.close()
|
||||
|
||||
# Abridging OGNT to minimum dataset required for an interlinear
|
||||
# Trimming OGNT to minimum dataset required for interlinear
|
||||
# 1-OGNTsort 2-TANTTsort 3-FEATURESsort1- 4-LevinsohnClauseID 5-OTquotation 〔6-BGBsortI|7-LTsortI|8-STsortI〕 〔9-Book|10-Chapter|11-Verse〕 〔12-OGNTk|13-OGNTu|14-OGNTa|15-lexeme|16-rmac|17-sn〕 〔18-BDAGentry|19-EDNTentry|20-MounceEntry|21-GoodrickKohlenbergerNumbers|22-LN-LouwNidaNumbers〕 〔23-transSBLcap|24-transSBL|25-modernGreek|26-Fonética_Transliteración〕 〔27-TBESG|28-IT|29-LT|30-ST|31-Español〕 〔32-PMpWord|33-PMfWord〕 〔34-Note|35-Mvar|36-Mlexeme|37-Mrmac|38-Msn|39-MTBESG〕
|
||||
newData = re.sub('(.*?)\t(.*?)\t(.*?)\t(.*?)\t(.*?)\t〔(.*?)|(.*?)|(.*?)〕\t〔(.*?)|(.*?)|(.*?)〕\t〔(.*?)|(.*?)|(.*?)|(.*?)|(.*?)|(.*?)〕\t〔(.*?)|(.*?)|(.*?)|(.*?)|(.*?)〕\t〔(.*?)|(.*?)|(.*?)|(.*?)〕\t〔(.*?)|(.*?)|(.*?)|(.*?)|(.*?)〕\t〔(.*?)|(.*?)〕\t〔(.*?)|(.*?)|(.*?)|(.*?)|(.*?)|(.*?)〕\n', r'\1\t\9-\10:\11\t\32\14\33\t\15\t\16\t\27\t\28\n', newData)
|
||||
|
||||
|
@ -20,17 +20,7 @@ newData = re.sub ('</pm><pm>',' ', newData)
|
|||
newData = re.sub ('</pm>','', newData)
|
||||
newData = re.sub ('<pm>','', newData)
|
||||
|
||||
# generate abridged file
|
||||
f = open(abridgedFile,'w',encoding='utf-8')
|
||||
f.write (newData)
|
||||
f.close()
|
||||
|
||||
# ---------------------------------------------------
|
||||
f = open(abridgedFile,'r',encoding="utf-8")
|
||||
newData = f.read()
|
||||
f.close()
|
||||
|
||||
# Fine-tuning (Book Name Abbreviation, Verbal emphasis)
|
||||
# Update Book Name Abbreviation
|
||||
searchReplace = (
|
||||
('40-', 'Mat '),
|
||||
('41-', 'Mar '),
|
||||
|
@ -63,15 +53,8 @@ searchReplace = (
|
|||
('\]\]', '⟧ '),
|
||||
(' —','—'),
|
||||
('—',' ——'),
|
||||
('(.*?\t.*?\t)(.*?)(\t.*?\tV-...-\d.\t)', r'\1**\2**\3'), # V-???-?? add bold emphasis
|
||||
('(.*?\t.*?\t)(.*?)(\t.*?\tV-2...-\d.\t)', r'\1**\2**\3'), # V-2???-?? add bold emphasis
|
||||
('(.*?\t.*?\t)(.*?)(\t.*?\tV-..P-...\t)', r'\1*\2*\3'), # V-??P-??? add italic emphasis
|
||||
('(.*?\t.*?\t)(.*?)(\t.*?\tV-2..P-...\t)', r'\1*\2*\3'), # V-2??P-??? add italic emphasis
|
||||
('(.*?\t.*?\t)(.*?)(\t.*?\tV-..N\t)', r'\1*\2*\3'), # V-??N add italic emphasis
|
||||
('(.*?\t.*?\t)(.*?)(\t.*?\tV-2..N\t)', r'\1*\2*\3') # V-2??N add italic emphasis
|
||||
)
|
||||
|
||||
|
||||
for search, replace in searchReplace:
|
||||
newData = re.sub(search, replace, newData)
|
||||
|
|
@ -0,0 +1,48 @@
|
|||
# Update all corrections to OGNT
|
||||
|
||||
import re
|
||||
|
||||
inputFile = "./tmp/OGNT-trimmed.txt"
|
||||
outputFile = "./OGNTa.txt"
|
||||
|
||||
|
||||
# modifications to morphological code
|
||||
ChangeList = (
|
||||
('018408', 'A-NSF-L'),
|
||||
('044656', 'A-NSM'),
|
||||
('044681', 'A-NSM'),
|
||||
('001339', 'V-I|AAI-3S'),
|
||||
('001446', 'N-N|VSF'),
|
||||
('001449', 'N-N|VSF'),
|
||||
('001456', 'N-N|VSF-L'),
|
||||
('002311', 'D-GPN|M'),
|
||||
('002313', 'T-GSM|N'),
|
||||
('002314', 'A-GSM|N'),
|
||||
('002332', 'T-DSN|M'),
|
||||
('002729', 'T-GSM|N'),
|
||||
)
|
||||
|
||||
|
||||
f = open(inputFile,'r',encoding="utf-8")
|
||||
Lines = f.readlines()
|
||||
f.close()
|
||||
|
||||
f = open(outputFile,'w',encoding='utf-8')
|
||||
f.write('\ufeff')
|
||||
flag = 0
|
||||
|
||||
for line in Lines:
|
||||
x = re.split("\t", line)
|
||||
for OGNTsort, rmac in ChangeList:
|
||||
if (x[0] == OGNTsort):
|
||||
f.write(x[0]+"\t"+x[1]+"\t"+x[2]+"\t"+x[3]+"\t"+rmac+"\t"+x[5]+"\t"+x[6])
|
||||
flag = 1
|
||||
break
|
||||
else:
|
||||
flag = 0
|
||||
continue
|
||||
if (flag == 0): f.write (line)
|
||||
|
||||
|
||||
f.close()
|
||||
|
|
@ -0,0 +1,28 @@
|
|||
# Mark emphasis on all verbals
|
||||
|
||||
import re
|
||||
|
||||
inputFile = "./OGNTa.txt"
|
||||
outputFile = "./tmp/OGNTa-marked.txt"
|
||||
|
||||
f = open(inputFile,'r',encoding="utf-8")
|
||||
Lines = f.readlines()
|
||||
f.close()
|
||||
|
||||
f = open(outputFile,'w',encoding="utf-8")
|
||||
|
||||
for line in Lines:
|
||||
x = re.split("\t", line)
|
||||
|
||||
# add emphasis for Verbs
|
||||
if (re.match(r'V-...-\d.',x[4])) or (re.match(r'V-....-\d.',x[4])):
|
||||
f.write(x[0]+"\t"+x[1]+"\t"+x[2]+"\t"+x[3]+"\t**"+x[4]+"**\t"+x[5]+"\t"+x[6])
|
||||
|
||||
# add emphasis for participles & infinitives
|
||||
elif (re.match(r'V-..P-...',x[4])) or (re.match(r'V-...P-...',x[4])) or (re.match(r'V-..N',x[4])) or (re.match(r'V-...N',x[4])):
|
||||
f.write(x[0]+"\t"+x[1]+"\t"+x[2]+"\t"+x[3]+"\t*"+x[4]+"*\t"+x[5]+"\t"+x[6])
|
||||
|
||||
else:
|
||||
f.write(x[0]+"\t"+x[1]+"\t"+x[2]+"\t"+x[3]+"\t"+x[4]+"\t"+x[5]+"\t"+x[6])
|
||||
|
||||
f.close()
|
|
@ -1,9 +1,7 @@
|
|||
# convert OGNTa into TheWord format
|
||||
|
||||
import re
|
||||
|
||||
inputFile = "OGNTa-Marked.txt"
|
||||
outputFile = "OGNTa-Ruby.nt"
|
||||
inputFile = "./tmp/OGNTa-marked.txt"
|
||||
outputFile = "./tmp/OGNTa-Ruby.nt"
|
||||
|
||||
# loading data
|
||||
f = open(inputFile,'r',encoding="utf-8")
|
File diff suppressed because it is too large
Load Diff
File diff suppressed because one or more lines are too long
File diff suppressed because it is too large
Load Diff
Loading…
Reference in New Issue