From 3140c028b70843fd57a429adb6e3f6ef7b2f3a1d Mon Sep 17 00:00:00 2001 From: Andrew Tavis McAllister Date: Mon, 18 Mar 2024 23:17:13 +0100 Subject: [PATCH 01/10] #73 minor file formatting and doc edit --- .../languages/French/translations/translate_words.py | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/src/scribe_data/extract_transform/languages/French/translations/translate_words.py b/src/scribe_data/extract_transform/languages/French/translations/translate_words.py index 62e47429..35b82eef 100644 --- a/src/scribe_data/extract_transform/languages/French/translations/translate_words.py +++ b/src/scribe_data/extract_transform/languages/French/translations/translate_words.py @@ -1,10 +1,9 @@ - """ Translates the French words queried from Wikidata to all other Scribe languages. Example ------- - python3 src/scribe_data/extract_transform/languages/English/translations/translate_words.py + python3 src/scribe_data/extract_transform/languages/French/translations/translate_words.py """ import json @@ -15,7 +14,7 @@ PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src" sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC) -from scribe_data.utils import translate_to_other_languages +from scribe_data.utils import translate_to_other_languages SRC_LANG = "French" translate_script_dir = os.path.dirname(os.path.abspath(__file__)) @@ -39,4 +38,4 @@ word_list=word_list, translations=translations, batch_size=100, -) \ No newline at end of file +) From a855b262210d88d89e8aa78b66e16d24dde581c0 Mon Sep 17 00:00:00 2001 From: Linfye <3158203624@qq.com> Date: Tue, 19 Mar 2024 16:42:24 +0800 Subject: [PATCH 02/10] Add GitHub Actions workflow for code checks --- .github/workflows/pr_ci.yaml | 47 ++++++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) create mode 100644 .github/workflows/pr_ci.yaml diff --git a/.github/workflows/pr_ci.yaml b/.github/workflows/pr_ci.yaml new file mode 100644 index 00000000..bb653fa8 --- /dev/null +++ b/.github/workflows/pr_ci.yaml @@ -0,0 +1,47 @@ +name: pr_ci +on: + pull_request: + branches: + - main + types: [opened, reopened, synchronize] + +jobs: + format_check: + strategy: + fail-fast: false + matrix: + os: + - ubuntu-latest + python-version: + - "3.9" + + runs-on: ${{ matrix.os }} + + name: Run PR Check + + steps: + - name: Checkout + uses: actions/checkout@v3 + + - name: Set up Python ${{ matrix.python-version }} + uses: actions/setup-python@v4 + with: + python-version: ${{ matrix.python-version }} + + - name: Install dependencies + run: | + python -m pip install --upgrade uv + uv venv + uv pip install -r requirements.txt + + - name: Activate virtualenv + run: | + . .venv/bin/activate + echo PATH=$PATH >> $GITHUB_ENV + + - name: Run ruff format - Formatting check + run: ruff . + + - name: Run ruff - Linting and import sorting check + if: always() + run: ruff . \ No newline at end of file From 45303c7b475b4a6128cb61fc725bde25231e567c Mon Sep 17 00:00:00 2001 From: Linfye <3158203624@qq.com> Date: Tue, 19 Mar 2024 16:50:02 +0800 Subject: [PATCH 03/10] test --- .github/workflows/pr_ci.yaml | 2 ++ 1 file changed, 2 insertions(+) diff --git a/.github/workflows/pr_ci.yaml b/.github/workflows/pr_ci.yaml index bb653fa8..f6b5a1ca 100644 --- a/.github/workflows/pr_ci.yaml +++ b/.github/workflows/pr_ci.yaml @@ -1,5 +1,7 @@ name: pr_ci on: + push: + branches: [main] pull_request: branches: - main From f86e9ac49f74774c92dd2881b48e05e6a5a7cc05 Mon Sep 17 00:00:00 2001 From: Linfye <3158203624@qq.com> Date: Tue, 19 Mar 2024 16:56:07 +0800 Subject: [PATCH 04/10] Small bugs with Ruff fixed --- .github/workflows/pr_ci.yaml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/.github/workflows/pr_ci.yaml b/.github/workflows/pr_ci.yaml index f6b5a1ca..ea8a3ec6 100644 --- a/.github/workflows/pr_ci.yaml +++ b/.github/workflows/pr_ci.yaml @@ -42,8 +42,8 @@ jobs: echo PATH=$PATH >> $GITHUB_ENV - name: Run ruff format - Formatting check - run: ruff . + run: ruff check . - name: Run ruff - Linting and import sorting check if: always() - run: ruff . \ No newline at end of file + run: ruff check . \ No newline at end of file From bf2f1763ebf18110e6435a4eaf9fa7a7f3312dbf Mon Sep 17 00:00:00 2001 From: Jag-Marcel Date: Tue, 19 Mar 2024 17:18:23 +0100 Subject: [PATCH 05/10] Portuguese translation to other Scribe languages --- .../translations/translate_words.py | 41 +++++++++++++++++++ 1 file changed, 41 insertions(+) create mode 100644 src/scribe_data/extract_transform/languages/Portuguese/translations/translate_words.py diff --git a/src/scribe_data/extract_transform/languages/Portuguese/translations/translate_words.py b/src/scribe_data/extract_transform/languages/Portuguese/translations/translate_words.py new file mode 100644 index 00000000..d170c943 --- /dev/null +++ b/src/scribe_data/extract_transform/languages/Portuguese/translations/translate_words.py @@ -0,0 +1,41 @@ +""" +Translates the Portuguese words queried from Wikidata to all other Scribe languages. + +Example +------- + python3 src/scribe_data/extract_transform/languages/Portuguese/translations/translate_words.py +""" + +import json +import os +import sys + +PATH_TO_SCRIBE_ORG = os.path.dirname(sys.path[0]).split("Scribe-Data")[0] +PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src" +sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC) + +from scribe_data.utils import translate_to_other_languages + +SRC_LANG = "Portuguese" +translate_script_dir = os.path.dirname(os.path.abspath(__file__)) +words_to_translate_path = os.path.join(translate_script_dir, "words_to_translate.json") + +with open(words_to_translate_path, "r", encoding="utf-8") as file: + json_data = json.load(file) + +word_list = [item["word"] for item in json_data] + +translations = {} +translated_words_path = os.path.join( + translate_script_dir, "../formatted_data/translated_words.json" +) +if os.path.exists(translated_words_path): + with open(translated_words_path, "r", encoding="utf-8") as file: + translations = json.load(file) + +translate_to_other_languages( + source_language=SRC_LANG, + word_list=word_list, + translations=translations, + batch_size=100, +) From 01861b1b35dad4d1df473f93524cbc1892e6d92c Mon Sep 17 00:00:00 2001 From: Abdulwasiu Apalowo Date: Wed, 20 Mar 2024 00:15:33 +0100 Subject: [PATCH 06/10] Add favicon to the docs --- docs/source/_static/ScribeFavicon.ico | Bin 0 -> 15406 bytes docs/source/conf.py | 3 +++ 2 files changed, 3 insertions(+) create mode 100644 docs/source/_static/ScribeFavicon.ico diff --git a/docs/source/_static/ScribeFavicon.ico b/docs/source/_static/ScribeFavicon.ico new file mode 100644 index 0000000000000000000000000000000000000000..29b6623a0068ab93ca12f5cf542f598c0a11c3a4 GIT binary patch literal 15406 zcmeHO+ix3H8XvU#2e1$O-lr9hJnh@IX)bM=f&}aXt+)t*kN^Qfn^i%Gn<`dIySxCR z^pb?6A!!m?x|O(;c0*ZG^_H|v?Iia2eu)#uNuAhn96NpZ_A@8oH_ITPBiU4?GM`h_iHFOX)pXy)BdVy+NMpp^9TNj&#d1vd`WkqT@_wi3hj)r;gl^^aBII{C6_ zD{Z(OYpWMnjCpD5N;^#tcT_~&^M4AT|D<5Uwi6u<0*Of*jl-WjH!VMJBK8p+e814n z@p&ULk`WtCwAYJcS!Y%{yIN==c!m7mwu-iTR}(SV-q}%4;U7N$_LU)Y_HEHl?`o!n zz!eIe*(1)~N4F7!?OmM>G(EJRrqBPU43Qt+Ay?Nnio1TG>7PCjHf-nlV!Oc7oS$aU ze>20C5qF=X*zm!E4cq#9ngt@?zeZDoZ?1~SnbtykY3D!IOezTW?I0C|2UJyA=jyrZnJ zwH?NLu9nEZXN~Vp8^5~`Zc)RbExGG5^KYoL<6Ucn@ATU=HPTB{!#!$%kHFwQvLlw! zf9bJYC&)4p)hUz7(8|h+GP2n$g@!&ZT35(8vK()3AR`uIZkqRBCfjG5SGAM&mCEt< zZIlQNi)-oO&CcEZ zPf{j1OG^tg%ltiGS-}RMfJuuRUe~Yy(gX*eXuweB)$8gf^WIb z6lG@<$@mk9uQNCFlcRlW6{r_>M!!z1e?0@wQ3m&5c_Biso`>^m)+TZtH2~{f8Q;-{ zwSQM5#nBfFScA`p?+n~_`bryYbAEN)Ls#!E^nDcZZ<7DN&lbg$>ttEV_)c828{871 z%aoe71GYPaonj+xVjV3wbU%VI?W1fuNuh6EDXgz$Ja;$N=>~B81g=>}pB3uCgSp%> z*dO<6XA31Fc3R0SQ{;bd-u7pRC)fF+?B1U1fBz-YasOR-{?`h;)7!J1j98lUig}mkPM(KVz;pQQ$e|+t##nqTzc*wV{pnv6A3tshVwXND^DpDb z(%*~k95dki$*&4Czom7G-&rc(Xlxt6cUmo>@{MSPZK%J6Y6+EZTuW^6ogA(qRKC%z zu#FtwNwq|!yuk0Jp7SI~(Q3~CzveuN6}gs;?Bgo(*&7*_G>tE{OHXg z*%)i+Kl>5nnJb~a89Cw>_}y_A&@A%e6}eR4SSiozJM%6jrgch0J(Qfe3y8WYbfJyx zxDS;$RZ~CbJzvQ2aL&hyyn7`d>|f@Uf z6nhQU2c5`Ajv!u!(#bdl&h5`#g9)!vuH(o7mjT+te1LOwD-^xfN45ihLw{_AR#0D2 zFEDBcRUbp^(fgjFCFD3cCg;OF&;@wBlyNKJYpOd4{+Dw6uQLD5G!FizZQ;+7dT@2& z8q)KVh?~WIxJmAlFTpo-j5WlV59Ily|LxFxxbN5Erz#u7@SS=U_aT>SO(H+-J@v|} z*I=e=IB>ni{Gr*vw`p6}5iG<+dm{x;zeU+pTs(gZ$aCv`yUBt3P)!^o|1o?cIFR$M z#$KiE1jf?jkNbr-!1Gc(c#ZU)$4uj!YCh=C1;hBs@oy+-JEk@zdXrKczMr^;siBXc zt;EGVK8Jl!?*83n9CT<)Oeop8$T6DEM<*{Km(;cS{-EC#LbC&++qiq>-jB9H#7YidOJ$ zm>umQS2y^Z*_6~7`A>j9>t#B0H~%-S6!`Xa>_^*!V+FuI@ZB5a>3_V85BELC44?au zmXmX09#4iYlJCTmWo=#9lU4>?%WeMsBsELc-4f89mlDuiEkGLFLWA$+HN_kc)U`a1NgN@gE!Q7yexE%i3KkhJ6UoE3+11^4wnd z&Fu+v@w13`r~m6ccn8PC{JDg9{;!@cw2^HKr9m^itxIB$fq}o1HA9RY{yqGCD@~q# zgC@@~URMC@;m3D;m+;H?R>w2tJNY6du~&oV&E@$Jg-^HQ_wA+{C-d=C0PDNF7MVr= zJF#|f!+)i=%Jrf;284BJt+_d#T7cbY|B`4Doy0y;){$A+E{f|&!;4zfz4307IDD?Ur zrd-VU$vRVwzf_C=HJ{gbpMdf{gJT#c8yHsXHMr+P;eP`9VY`7*%RMGm#I|IwiQ@ls n{GK^jvDf9EkG20#P%ZZeSrYriLloJ-!1kbffA@M|%{}lloI*h6 literal 0 HcmV?d00001 diff --git a/docs/source/conf.py b/docs/source/conf.py index 716465b1..4f54e081 100644 --- a/docs/source/conf.py +++ b/docs/source/conf.py @@ -188,6 +188,9 @@ "display_version": True, } +# Adding favicon to the docs +html_favicon = "_static/ScribeFavicon.ico" + # Importing custom css for theme customization. html_css_files = [ "custom.css", From 199e9187e84ac4d86c3d23ae623c4a24541a9e6a Mon Sep 17 00:00:00 2001 From: Andrew Tavis McAllister Date: Wed, 20 Mar 2024 00:27:20 +0100 Subject: [PATCH 07/10] #107 fix of comment punctuation --- docs/source/conf.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/source/conf.py b/docs/source/conf.py index 4f54e081..7ba02728 100644 --- a/docs/source/conf.py +++ b/docs/source/conf.py @@ -188,7 +188,7 @@ "display_version": True, } -# Adding favicon to the docs +# Adding favicon to the docs. html_favicon = "_static/ScribeFavicon.ico" # Importing custom css for theme customization. From fe52d3dd77ef274fc39e323f3370c9f5576d73be Mon Sep 17 00:00:00 2001 From: Andrew Tavis McAllister Date: Wed, 20 Mar 2024 00:47:14 +0100 Subject: [PATCH 08/10] #107 minor doc favicon update: icon larger and rounded corners --- docs/source/_static/ScribeFavicon.ico | Bin 15406 -> 15406 bytes 1 file changed, 0 insertions(+), 0 deletions(-) diff --git a/docs/source/_static/ScribeFavicon.ico b/docs/source/_static/ScribeFavicon.ico index 29b6623a0068ab93ca12f5cf542f598c0a11c3a4..7c9c28f9ee26288ccb6a2cead9aee5ae0759dcec 100644 GIT binary patch literal 15406 zcmeHOS#w;~5uQ}|0q~G_Kc#r&DNn(YwOFz(3|~KHr)(Zu`+ke7-`+9(&Bwf8Xc3_&uNR zQP`jhdbo0sq<>d)*S>r8!?n|ZED_V}TeBx+x+XV8h--UN9AeS!y(zKldsAgOsNJ9H zC~odc73E16)y`WdEvH|XuFD6c^U~cxn?S`5sYM?}LqVF;Ut2BRmkK0&?vE1wl=zcN z6WSdY-j~t-76}~wiPYz(3Hvq{rc1Q$sDw_wCgc}F+v(S2q&Fae(k;d|P@LgJ>yJwN zN3S{lq6}eMF<(1!{vBty^M(WuZIa-DOu5x?Oxm#qEfr5o+o@NRyZDM^aJX=y3jE0O9mQ` zN!NwHNn7=EcSZY&7iFx!St4g&74{?A%CemPuRm~x!xv>S=(+Hg!#+f)6#WlpFAE(< zHaOw(4MLD#YCBS~VLDQ=QN9^AOm|jpe7CD=Qw(rAD>n(LVu5yyeUm;EmLTMFW(|-E z@cA^~--SP?K6EAb@%QkIiQ3PZn%uR{3bv#4N#8Y~@P+4;i)(w<;yJZiZTQ}k64htq zs#EyBzSlgP`HY?e>Q-8RV_zzK=(9cr&wN7Lsj>=s`jDG=FBpn=NNt(T|t@djtKyVi``bt&KL%W+)Lx4$Ue z>~&g>&iJo~f8Fn>UfYRuA${P`lMeSJT!+Z#AH>Ivk5h!b6%ac1yujJ5_JqHQj~_gc;Slg|u2UcU`wP}_uZTUJtFx)fmD)P;DpwlU zV=Y4`el1fIqcSlvAg$Fqyzw*5-mxw2zf}DB>#(QHbb^Q>fHfzA=&$_3?F_d+_ORT? z8sI+j7jDEpu~nw0r=|1!TbOsIG{a95XxoVw-1*m(N&xpcW!?YzhxA^`ce?+ZC-b2v ziN5!8zBHFS!5GZ=W*!BZGSq&>_`X$JX2v&q?30@gu9xts7tH|&l}b~Q@h_2&e(6L$ zensX(=b2ZM>(5{xUb<0QIJd$yCt7>d_#WxF2!9*YzwzB#n&oi69zOM=v2p#Uv#&ub z;#1zGnQp1N|-&gNT|K)$h5xw%EL)bE#Ur2uoeLGL?h>uS{p|WhD zFQxjO)n1-WyZATPYPG}oHfuk;0WksmUSk_{R(l2Y`dxUxD84W8ZMqTPsB=NxO6&2h zNgvYTed{Wvj93MIG*Ssa_&$!{JK6XHHNLA58+0qB@2cF`k8kn!^t;@q{6<&Ua^+P= zsxq4{Qg6P2JF5{x^`>ZdwaF2PP08DUk7euWi$3}NJzrkn|3%I`2~xDa9l+i4BvAWm zbAR|q&7QTpujZy)M~*dS=SRphXF?>(RhKAVDf=tT8zaV=57+Ky%o_W(+_lB?#jUYv z{7O}BQ(LFJQrk{>Tc^BIwXvz{Kx2$q*BxsggKSo=C^288ddd@Z$z-cwk2yU4(luTW zD<5z3nw!@=y;9r8=2zVwv0vMZYvJXn=F3S@t~#acWAi$O%2lUS<+h#jv{5^yi?T=T zH`tf4EC97r`oP$GdAb|>xCWY^(|p}b&JMXUqo1JstDpQ(FmrQm)?3sfk zkau(QlpeKZ%BzjGZJLZ<4SPFxY4djeQhBAeo$|I$d8KM&Q(LFJQrk{>Tc^CCUVfCh zOdD1n)8sVSwq>?0d0VHpwrr*BO@7sl9ko#8KglyUYVxCAp4ZCxYQ7ii!rJLfPS~3uFHnOv z^#G$&o_T8n5EWE4Qxsb>_H<#5_A? z{)10A15M{mekC?FArnJgE^dRaG~g>XIc9v1-s+I%V=p5w?&jt-FRwKL(m0Su!`y@j z976ofpSgLhTVb3VKrXfXXVP@!nYpN->{$;<^oe~Iw0~B*zuqg;SU2XEM*3QCFTZTo zTH{mNfS3ukkxw^u2Il_#2RDnx&wOm%zV%X{mul()YNu3d1%@JL9&dZR+9{3eSz}0Q z&oxDE_hPOy9h)+9814z8{_*_G*j8U1SL+O!*j!l|-X|V001P?zw$49d9f~A|C#Q1R!x-}0ke%pVtF;t&S zmrORtp7(LdRv8SQ6XrdqrY42I$w2AWS#!{_wBCWbf)gxxa@P7c=4CmJh~KV-*!C(< zl&PF!ChC&O674ysAf6?++rFBaL-Pd*mTaCi9>=oLRQjYd*y8?vdH*!zWtp0bj<3}2 zqr9zCUa8vH)Yd7lly+R-rqXTBNar=wCXjcY9GAWu<(NZ`nS*OHyB37_B_2P{>@?Y4C|+-3 zamPnJi7^ys3gaKr_1E}|(r}GTt%!9Y53ao{=QYg4c(ifnbMNf2W_Uif9N8fg!@cJB z%sO57SAS>iO5<_sSgcu@#lbQQmSu#2M&6Q)_?D6SC z!E271VdMS`iPj!7*MRSa!N5oHI$S)ic>EWP9nX9PQ1@s291nFjhdjsgV^88D6?6sx z)wW%$Ea|yaC^0;TSU(%@^GnNBnpbYl}?g=>7XkSoTEAjs38nLd(crX`J6UBbA>x+My z^9zi9VgU7~Q@f2FZC!h}&d8cyYxx#usMU>s9P1w}%tp-*ds5Wvx<7y4nZ!8=UcY;d z_TxKQYm9^UnIHSH@W*eOnlNLZLcOZ%{M(4xtx>AI)+t%53>`^`zXYT>%1FnhdyB{=X|Mh%YL#xiw3)w4+&AH~Z_D`YUU#j=2c_qW_fY%IGBr-xs=ZyO z43%#Yd;Oabe>3Cf+;|r9$Tn%K*k&mCyTP^FzJUF92~}*z`ed7WDefC-#`7+WGoxeJ zgYr60PmUn=zZx66-l}nHowl`fJ>uFTx2^l9sR%XQ0~w~SN3ntC&@ zlLyvbmu8RH9Nw#;s^^@M?nW>6F^SgXOKTZw&eqsoebOfao!r#Q%X6GtHK^^6 z_DKxC`KhsiRYh!kKt{t~O61f|Q(JEyq(mr!<+3EmJ$Cwk{d3c6ts4XF;&W?s*lP!p=Rz;+w4D3rpb7ogVFOZ$}7De_Kdx|dgE^RHvf;qSQHwM#%EKtvFU2tGiJoU`}XNg zk91dUDn=|ZoZm5Lf=JPJ&jWcp+XmLTq5EhbW6X@5XHd)>a2*iebpY2Q2eIZL{v6CF m2XmR>T^Z-6Ha5Sq_VCHLuXk4Eyri)+{%`-jU4d`90{;Vk?16^> literal 15406 zcmeHO+ix3H8XvU#2e1$O-lr9hJnh@IX)bM=f&}aXt+)t*kN^Qfn^i%Gn<`dIySxCR z^pb?6A!!m?x|O(;c0*ZG^_H|v?Iia2eu)#uNuAhn96NpZ_A@8oH_ITPBiU4?GM`h_iHFOX)pXy)BdVy+NMpp^9TNj&#d1vd`WkqT@_wi3hj)r;gl^^aBII{C6_ zD{Z(OYpWMnjCpD5N;^#tcT_~&^M4AT|D<5Uwi6u<0*Of*jl-WjH!VMJBK8p+e814n z@p&ULk`WtCwAYJcS!Y%{yIN==c!m7mwu-iTR}(SV-q}%4;U7N$_LU)Y_HEHl?`o!n zz!eIe*(1)~N4F7!?OmM>G(EJRrqBPU43Qt+Ay?Nnio1TG>7PCjHf-nlV!Oc7oS$aU ze>20C5qF=X*zm!E4cq#9ngt@?zeZDoZ?1~SnbtykY3D!IOezTW?I0C|2UJyA=jyrZnJ zwH?NLu9nEZXN~Vp8^5~`Zc)RbExGG5^KYoL<6Ucn@ATU=HPTB{!#!$%kHFwQvLlw! zf9bJYC&)4p)hUz7(8|h+GP2n$g@!&ZT35(8vK()3AR`uIZkqRBCfjG5SGAM&mCEt< zZIlQNi)-oO&CcEZ zPf{j1OG^tg%ltiGS-}RMfJuuRUe~Yy(gX*eXuweB)$8gf^WIb z6lG@<$@mk9uQNCFlcRlW6{r_>M!!z1e?0@wQ3m&5c_Biso`>^m)+TZtH2~{f8Q;-{ zwSQM5#nBfFScA`p?+n~_`bryYbAEN)Ls#!E^nDcZZ<7DN&lbg$>ttEV_)c828{871 z%aoe71GYPaonj+xVjV3wbU%VI?W1fuNuh6EDXgz$Ja;$N=>~B81g=>}pB3uCgSp%> z*dO<6XA31Fc3R0SQ{;bd-u7pRC)fF+?B1U1fBz-YasOR-{?`h;)7!J1j98lUig}mkPM(KVz;pQQ$e|+t##nqTzc*wV{pnv6A3tshVwXND^DpDb z(%*~k95dki$*&4Czom7G-&rc(Xlxt6cUmo>@{MSPZK%J6Y6+EZTuW^6ogA(qRKC%z zu#FtwNwq|!yuk0Jp7SI~(Q3~CzveuN6}gs;?Bgo(*&7*_G>tE{OHXg z*%)i+Kl>5nnJb~a89Cw>_}y_A&@A%e6}eR4SSiozJM%6jrgch0J(Qfe3y8WYbfJyx zxDS;$RZ~CbJzvQ2aL&hyyn7`d>|f@Uf z6nhQU2c5`Ajv!u!(#bdl&h5`#g9)!vuH(o7mjT+te1LOwD-^xfN45ihLw{_AR#0D2 zFEDBcRUbp^(fgjFCFD3cCg;OF&;@wBlyNKJYpOd4{+Dw6uQLD5G!FizZQ;+7dT@2& z8q)KVh?~WIxJmAlFTpo-j5WlV59Ily|LxFxxbN5Erz#u7@SS=U_aT>SO(H+-J@v|} z*I=e=IB>ni{Gr*vw`p6}5iG<+dm{x;zeU+pTs(gZ$aCv`yUBt3P)!^o|1o?cIFR$M z#$KiE1jf?jkNbr-!1Gc(c#ZU)$4uj!YCh=C1;hBs@oy+-JEk@zdXrKczMr^;siBXc zt;EGVK8Jl!?*83n9CT<)Oeop8$T6DEM<*{Km(;cS{-EC#LbC&++qiq>-jB9H#7YidOJ$ zm>umQS2y^Z*_6~7`A>j9>t#B0H~%-S6!`Xa>_^*!V+FuI@ZB5a>3_V85BELC44?au zmXmX09#4iYlJCTmWo=#9lU4>?%WeMsBsELc-4f89mlDuiEkGLFLWA$+HN_kc)U`a1NgN@gE!Q7yexE%i3KkhJ6UoE3+11^4wnd z&Fu+v@w13`r~m6ccn8PC{JDg9{;!@cw2^HKr9m^itxIB$fq}o1HA9RY{yqGCD@~q# zgC@@~URMC@;m3D;m+;H?R>w2tJNY6du~&oV&E@$Jg-^HQ_wA+{C-d=C0PDNF7MVr= zJF#|f!+)i=%Jrf;284BJt+_d#T7cbY|B`4Doy0y;){$A+E{f|&!;4zfz4307IDD?Ur zrd-VU$vRVwzf_C=HJ{gbpMdf{gJT#c8yHsXHMr+P;eP`9VY`7*%RMGm#I|IwiQ@ls n{GK^jvDf9EkG20#P%ZZeSrYriLloJ-!1kbffA@M|%{}lloI*h6 From 6ab8d17d4206090431feb6d4133f36b0a389f6cf Mon Sep 17 00:00:00 2001 From: Andrew Tavis McAllister Date: Wed, 20 Mar 2024 03:22:04 +0100 Subject: [PATCH 09/10] #109 fix all Ruff formatting and linting errors --- .github/workflows/pr_ci.yaml | 2 +- src/scribe_data/checkquery.py | 5 ++- .../extract_transform/extract_wiki.py | 8 ++--- .../languages/English/nouns/format_nouns.py | 2 +- .../English/translations/translate_words.py | 2 +- .../languages/English/verbs/format_verbs.py | 2 +- .../languages/French/nouns/format_nouns.py | 6 +++- .../French/translations/translate_words.py | 2 +- .../languages/French/verbs/format_verbs.py | 2 +- .../languages/German/nouns/format_nouns.py | 6 +++- .../prepositions/format_prepositions.py | 2 +- .../languages/German/verbs/format_verbs.py | 2 +- .../languages/Italian/nouns/format_nouns.py | 6 +++- .../languages/Italian/verbs/format_verbs.py | 2 +- .../Portuguese/nouns/format_nouns.py | 6 +++- .../Portuguese/verbs/format_verbs.py | 2 +- .../languages/Russian/nouns/format_nouns.py | 6 +++- .../prepositions/format_prepositions.py | 2 +- .../Russian/translations/translate_words.py | 2 +- .../languages/Russian/verbs/format_verbs.py | 2 +- .../languages/Spanish/nouns/format_nouns.py | 6 +++- .../languages/Spanish/verbs/format_verbs.py | 2 +- .../languages/Swedish/nouns/format_nouns.py | 6 +++- .../languages/Swedish/verbs/format_verbs.py | 2 +- .../extract_transform/languages/__init__.py | 0 .../extract_transform/process_unicode.py | 3 +- .../extract_transform/process_wiki.py | 1 - src/scribe_data/load/data_to_sqlite.py | 36 +++++++++---------- src/scribe_data/load/send_dbs_to_scribe.py | 2 +- 29 files changed, 76 insertions(+), 51 deletions(-) create mode 100644 src/scribe_data/extract_transform/languages/__init__.py diff --git a/.github/workflows/pr_ci.yaml b/.github/workflows/pr_ci.yaml index ea8a3ec6..0f317ee6 100644 --- a/.github/workflows/pr_ci.yaml +++ b/.github/workflows/pr_ci.yaml @@ -46,4 +46,4 @@ jobs: - name: Run ruff - Linting and import sorting check if: always() - run: ruff check . \ No newline at end of file + run: ruff check . diff --git a/src/scribe_data/checkquery.py b/src/scribe_data/checkquery.py index 71ab4410..1a035f2a 100755 --- a/src/scribe_data/checkquery.py +++ b/src/scribe_data/checkquery.py @@ -24,6 +24,7 @@ """ import argparse +import contextlib import math import os import subprocess @@ -304,12 +305,10 @@ def check_positive_int(value: str, err_msg: str) -> int: ------ argparse.ArgumentTypeError """ - try: + with contextlib.suppress(ValueError): number = int(value) if number >= 1: return number - except ValueError: - pass raise argparse.ArgumentTypeError(err_msg) diff --git a/src/scribe_data/extract_transform/extract_wiki.py b/src/scribe_data/extract_transform/extract_wiki.py index 1466fd8d..2f98dca0 100644 --- a/src/scribe_data/extract_transform/extract_wiki.py +++ b/src/scribe_data/extract_transform/extract_wiki.py @@ -320,9 +320,9 @@ def parse_to_ndjson( print(f"Making {output_dir} directory for the output") os.makedirs(output_dir) - if multicore == True: + if multicore: num_cores = os.cpu_count() - elif multicore == False: + elif not multicore: num_cores = 1 elif isinstance(multicore, int): num_cores = multicore @@ -372,8 +372,8 @@ def read_and_combine_json(file_path): data = [] with open(file_path, "r", encoding="utf-8") as f: - for l in f: - data.append(json.loads(l)) + for line in f: + data.append(json.loads(line)) return data diff --git a/src/scribe_data/extract_transform/languages/English/nouns/format_nouns.py b/src/scribe_data/extract_transform/languages/English/nouns/format_nouns.py index 502a2f22..5356c054 100644 --- a/src/scribe_data/extract_transform/languages/English/nouns/format_nouns.py +++ b/src/scribe_data/extract_transform/languages/English/nouns/format_nouns.py @@ -10,7 +10,7 @@ PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src" sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC) -from scribe_data.utils import export_formatted_data, load_queried_data +from scribe_data.utils import export_formatted_data, load_queried_data # noqa: E402 file_path = sys.argv[0] diff --git a/src/scribe_data/extract_transform/languages/English/translations/translate_words.py b/src/scribe_data/extract_transform/languages/English/translations/translate_words.py index 944c9cd4..fad6e9ec 100644 --- a/src/scribe_data/extract_transform/languages/English/translations/translate_words.py +++ b/src/scribe_data/extract_transform/languages/English/translations/translate_words.py @@ -14,7 +14,7 @@ PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src" sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC) -from scribe_data.utils import translate_to_other_languages +from scribe_data.utils import translate_to_other_languages # noqa: E402 SRC_LANG = "English" translate_script_dir = os.path.dirname(os.path.abspath(__file__)) diff --git a/src/scribe_data/extract_transform/languages/English/verbs/format_verbs.py b/src/scribe_data/extract_transform/languages/English/verbs/format_verbs.py index 24219922..92c42927 100644 --- a/src/scribe_data/extract_transform/languages/English/verbs/format_verbs.py +++ b/src/scribe_data/extract_transform/languages/English/verbs/format_verbs.py @@ -10,7 +10,7 @@ PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src" sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC) -from scribe_data.utils import export_formatted_data, load_queried_data +from scribe_data.utils import export_formatted_data, load_queried_data # noqa: E402 file_path = sys.argv[0] diff --git a/src/scribe_data/extract_transform/languages/French/nouns/format_nouns.py b/src/scribe_data/extract_transform/languages/French/nouns/format_nouns.py index 569c81ff..7ea0576d 100644 --- a/src/scribe_data/extract_transform/languages/French/nouns/format_nouns.py +++ b/src/scribe_data/extract_transform/languages/French/nouns/format_nouns.py @@ -10,7 +10,11 @@ PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src" sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC) -from scribe_data.utils import export_formatted_data, load_queried_data, map_genders +from scribe_data.utils import ( # noqa: E402 + export_formatted_data, + load_queried_data, + map_genders, +) file_path = sys.argv[0] diff --git a/src/scribe_data/extract_transform/languages/French/translations/translate_words.py b/src/scribe_data/extract_transform/languages/French/translations/translate_words.py index 35b82eef..a8177bdb 100644 --- a/src/scribe_data/extract_transform/languages/French/translations/translate_words.py +++ b/src/scribe_data/extract_transform/languages/French/translations/translate_words.py @@ -14,7 +14,7 @@ PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src" sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC) -from scribe_data.utils import translate_to_other_languages +from scribe_data.utils import translate_to_other_languages # noqa: E402 SRC_LANG = "French" translate_script_dir = os.path.dirname(os.path.abspath(__file__)) diff --git a/src/scribe_data/extract_transform/languages/French/verbs/format_verbs.py b/src/scribe_data/extract_transform/languages/French/verbs/format_verbs.py index 8310504a..c2b9e367 100644 --- a/src/scribe_data/extract_transform/languages/French/verbs/format_verbs.py +++ b/src/scribe_data/extract_transform/languages/French/verbs/format_verbs.py @@ -10,7 +10,7 @@ PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src" sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC) -from scribe_data.utils import export_formatted_data, load_queried_data +from scribe_data.utils import export_formatted_data, load_queried_data # noqa: E402 file_path = sys.argv[0] diff --git a/src/scribe_data/extract_transform/languages/German/nouns/format_nouns.py b/src/scribe_data/extract_transform/languages/German/nouns/format_nouns.py index a28c8700..557903c5 100644 --- a/src/scribe_data/extract_transform/languages/German/nouns/format_nouns.py +++ b/src/scribe_data/extract_transform/languages/German/nouns/format_nouns.py @@ -10,7 +10,11 @@ PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src" sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC) -from scribe_data.utils import export_formatted_data, load_queried_data, map_genders +from scribe_data.utils import ( # noqa: E402 + export_formatted_data, + load_queried_data, + map_genders, +) file_path = sys.argv[0] diff --git a/src/scribe_data/extract_transform/languages/German/prepositions/format_prepositions.py b/src/scribe_data/extract_transform/languages/German/prepositions/format_prepositions.py index 69486dcb..d03e209b 100644 --- a/src/scribe_data/extract_transform/languages/German/prepositions/format_prepositions.py +++ b/src/scribe_data/extract_transform/languages/German/prepositions/format_prepositions.py @@ -10,7 +10,7 @@ PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src" sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC) -from scribe_data.utils import export_formatted_data, load_queried_data +from scribe_data.utils import export_formatted_data, load_queried_data # noqa: E402 file_path = sys.argv[0] diff --git a/src/scribe_data/extract_transform/languages/German/verbs/format_verbs.py b/src/scribe_data/extract_transform/languages/German/verbs/format_verbs.py index 042170bd..5a6bda6e 100644 --- a/src/scribe_data/extract_transform/languages/German/verbs/format_verbs.py +++ b/src/scribe_data/extract_transform/languages/German/verbs/format_verbs.py @@ -15,7 +15,7 @@ PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src" sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC) -from scribe_data.utils import export_formatted_data, load_queried_data +from scribe_data.utils import export_formatted_data, load_queried_data # noqa: E402 file_path = sys.argv[0] diff --git a/src/scribe_data/extract_transform/languages/Italian/nouns/format_nouns.py b/src/scribe_data/extract_transform/languages/Italian/nouns/format_nouns.py index 7c618616..99566f59 100644 --- a/src/scribe_data/extract_transform/languages/Italian/nouns/format_nouns.py +++ b/src/scribe_data/extract_transform/languages/Italian/nouns/format_nouns.py @@ -10,7 +10,11 @@ PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src" sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC) -from scribe_data.utils import export_formatted_data, load_queried_data, map_genders +from scribe_data.utils import ( # noqa: E402 + export_formatted_data, + load_queried_data, + map_genders, +) file_path = sys.argv[0] diff --git a/src/scribe_data/extract_transform/languages/Italian/verbs/format_verbs.py b/src/scribe_data/extract_transform/languages/Italian/verbs/format_verbs.py index 6b905c21..95bb2a35 100644 --- a/src/scribe_data/extract_transform/languages/Italian/verbs/format_verbs.py +++ b/src/scribe_data/extract_transform/languages/Italian/verbs/format_verbs.py @@ -10,7 +10,7 @@ PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src" sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC) -from scribe_data.utils import export_formatted_data, load_queried_data +from scribe_data.utils import export_formatted_data, load_queried_data # noqa: E402 file_path = sys.argv[0] diff --git a/src/scribe_data/extract_transform/languages/Portuguese/nouns/format_nouns.py b/src/scribe_data/extract_transform/languages/Portuguese/nouns/format_nouns.py index 280aeda5..6c84b6ec 100644 --- a/src/scribe_data/extract_transform/languages/Portuguese/nouns/format_nouns.py +++ b/src/scribe_data/extract_transform/languages/Portuguese/nouns/format_nouns.py @@ -10,7 +10,11 @@ PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src" sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC) -from scribe_data.utils import export_formatted_data, load_queried_data, map_genders +from scribe_data.utils import ( # noqa: E402 + export_formatted_data, + load_queried_data, + map_genders, +) file_path = sys.argv[0] diff --git a/src/scribe_data/extract_transform/languages/Portuguese/verbs/format_verbs.py b/src/scribe_data/extract_transform/languages/Portuguese/verbs/format_verbs.py index 285bb7cf..c71ed07f 100644 --- a/src/scribe_data/extract_transform/languages/Portuguese/verbs/format_verbs.py +++ b/src/scribe_data/extract_transform/languages/Portuguese/verbs/format_verbs.py @@ -10,7 +10,7 @@ PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src" sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC) -from scribe_data.utils import export_formatted_data, load_queried_data +from scribe_data.utils import export_formatted_data, load_queried_data # noqa: E402 file_path = sys.argv[0] diff --git a/src/scribe_data/extract_transform/languages/Russian/nouns/format_nouns.py b/src/scribe_data/extract_transform/languages/Russian/nouns/format_nouns.py index 4c3ae853..0fb2d20a 100644 --- a/src/scribe_data/extract_transform/languages/Russian/nouns/format_nouns.py +++ b/src/scribe_data/extract_transform/languages/Russian/nouns/format_nouns.py @@ -10,7 +10,11 @@ PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src" sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC) -from scribe_data.utils import export_formatted_data, load_queried_data, map_genders +from scribe_data.utils import ( # noqa: E402 + export_formatted_data, + load_queried_data, + map_genders, +) file_path = sys.argv[0] diff --git a/src/scribe_data/extract_transform/languages/Russian/prepositions/format_prepositions.py b/src/scribe_data/extract_transform/languages/Russian/prepositions/format_prepositions.py index 4dd10a13..8702881e 100644 --- a/src/scribe_data/extract_transform/languages/Russian/prepositions/format_prepositions.py +++ b/src/scribe_data/extract_transform/languages/Russian/prepositions/format_prepositions.py @@ -10,7 +10,7 @@ PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src" sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC) -from scribe_data.utils import export_formatted_data, load_queried_data +from scribe_data.utils import export_formatted_data, load_queried_data # noqa: E402 file_path = sys.argv[0] diff --git a/src/scribe_data/extract_transform/languages/Russian/translations/translate_words.py b/src/scribe_data/extract_transform/languages/Russian/translations/translate_words.py index a9c295fc..a2b78e8f 100644 --- a/src/scribe_data/extract_transform/languages/Russian/translations/translate_words.py +++ b/src/scribe_data/extract_transform/languages/Russian/translations/translate_words.py @@ -14,7 +14,7 @@ PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src" sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC) -from scribe_data.utils import translate_to_other_languages +from scribe_data.utils import translate_to_other_languages # noqa: E402 SRC_LANG = "Russian" translate_script_dir = os.path.dirname(os.path.abspath(__file__)) diff --git a/src/scribe_data/extract_transform/languages/Russian/verbs/format_verbs.py b/src/scribe_data/extract_transform/languages/Russian/verbs/format_verbs.py index 4c914bee..7b3d49a1 100644 --- a/src/scribe_data/extract_transform/languages/Russian/verbs/format_verbs.py +++ b/src/scribe_data/extract_transform/languages/Russian/verbs/format_verbs.py @@ -10,7 +10,7 @@ PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src" sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC) -from scribe_data.utils import export_formatted_data, load_queried_data +from scribe_data.utils import export_formatted_data, load_queried_data # noqa: E402 file_path = sys.argv[0] diff --git a/src/scribe_data/extract_transform/languages/Spanish/nouns/format_nouns.py b/src/scribe_data/extract_transform/languages/Spanish/nouns/format_nouns.py index 4339fb38..ff552e16 100644 --- a/src/scribe_data/extract_transform/languages/Spanish/nouns/format_nouns.py +++ b/src/scribe_data/extract_transform/languages/Spanish/nouns/format_nouns.py @@ -10,7 +10,11 @@ PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src" sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC) -from scribe_data.utils import export_formatted_data, load_queried_data, map_genders +from scribe_data.utils import ( # noqa: E402 + export_formatted_data, + load_queried_data, + map_genders, +) file_path = sys.argv[0] diff --git a/src/scribe_data/extract_transform/languages/Spanish/verbs/format_verbs.py b/src/scribe_data/extract_transform/languages/Spanish/verbs/format_verbs.py index 43ede52e..e69d439d 100644 --- a/src/scribe_data/extract_transform/languages/Spanish/verbs/format_verbs.py +++ b/src/scribe_data/extract_transform/languages/Spanish/verbs/format_verbs.py @@ -10,7 +10,7 @@ PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src" sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC) -from scribe_data.utils import export_formatted_data, load_queried_data +from scribe_data.utils import export_formatted_data, load_queried_data # noqa: E402 file_path = sys.argv[0] diff --git a/src/scribe_data/extract_transform/languages/Swedish/nouns/format_nouns.py b/src/scribe_data/extract_transform/languages/Swedish/nouns/format_nouns.py index 6fca6254..cf717068 100644 --- a/src/scribe_data/extract_transform/languages/Swedish/nouns/format_nouns.py +++ b/src/scribe_data/extract_transform/languages/Swedish/nouns/format_nouns.py @@ -10,7 +10,11 @@ PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src" sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC) -from scribe_data.utils import export_formatted_data, load_queried_data, map_genders +from scribe_data.utils import ( # noqa: E402 + export_formatted_data, + load_queried_data, + map_genders, +) file_path = sys.argv[0] diff --git a/src/scribe_data/extract_transform/languages/Swedish/verbs/format_verbs.py b/src/scribe_data/extract_transform/languages/Swedish/verbs/format_verbs.py index 01767e6e..c58b6de8 100644 --- a/src/scribe_data/extract_transform/languages/Swedish/verbs/format_verbs.py +++ b/src/scribe_data/extract_transform/languages/Swedish/verbs/format_verbs.py @@ -10,7 +10,7 @@ PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src" sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC) -from scribe_data.utils import export_formatted_data, load_queried_data +from scribe_data.utils import export_formatted_data, load_queried_data # noqa: E402 file_path = sys.argv[0] diff --git a/src/scribe_data/extract_transform/languages/__init__.py b/src/scribe_data/extract_transform/languages/__init__.py new file mode 100644 index 00000000..e69de29b diff --git a/src/scribe_data/extract_transform/process_unicode.py b/src/scribe_data/extract_transform/process_unicode.py index 5185cd1e..4297f56d 100644 --- a/src/scribe_data/extract_transform/process_unicode.py +++ b/src/scribe_data/extract_transform/process_unicode.py @@ -8,7 +8,6 @@ import csv import fileinput import json -import re from importlib.resources import files import emoji @@ -16,7 +15,7 @@ from tqdm.auto import tqdm from scribe_data.extract_transform.emoji_utils import get_emoji_codes_to_ignore -from scribe_data.load.update_utils import ( +from scribe_data.utils import ( get_language_iso, get_path_from_et_dir, ) diff --git a/src/scribe_data/extract_transform/process_wiki.py b/src/scribe_data/extract_transform/process_wiki.py index c937d05a..227e12ab 100644 --- a/src/scribe_data/extract_transform/process_wiki.py +++ b/src/scribe_data/extract_transform/process_wiki.py @@ -19,7 +19,6 @@ from tqdm.auto import tqdm from scribe_data.utils import ( - get_ios_data_path, get_language_qid, get_language_words_to_ignore, get_language_words_to_remove, diff --git a/src/scribe_data/load/data_to_sqlite.py b/src/scribe_data/load/data_to_sqlite.py index 50adde11..09cb2c34 100644 --- a/src/scribe_data/load/data_to_sqlite.py +++ b/src/scribe_data/load/data_to_sqlite.py @@ -23,7 +23,7 @@ PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src" sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC) -from scribe_data.utils import get_ios_data_path, get_language_iso +from scribe_data.utils import get_language_iso # noqa: E402 PATH_TO_ET_FILES = "../extract_transform/" @@ -76,32 +76,32 @@ languages_update = current_languages if languages is None else languages language_word_type_dict = { - l: [ + lang: [ f.split(".json")[0] - for f in os.listdir(f"{PATH_TO_ET_FILES}{l}/formatted_data") + for f in os.listdir(f"{PATH_TO_ET_FILES}{lang}/formatted_data") if f.split(".json")[0] in word_types ] - for l in languages_update + for lang in languages_update } print( f"Creating SQLite databases for the following languages: {', '.join(languages_update)}" ) -for l in tqdm( +for lang in tqdm( language_word_type_dict, desc="Databases created", unit="dbs", ): - if language_word_type_dict[l] != []: + if language_word_type_dict[lang] != []: maybe_over = "" # output string formatting variable (see below) if os.path.exists( - f"databases/{get_language_iso(l).upper()}LanguageData.sqlite" + f"databases/{get_language_iso(lang).upper()}LanguageData.sqlite" ): - os.remove(f"databases/{get_language_iso(l).upper()}LanguageData.sqlite") + os.remove(f"databases/{get_language_iso(lang).upper()}LanguageData.sqlite") maybe_over = "over" connection = sqlite3.connect( - f"databases/{get_language_iso(l).upper()}LanguageData.sqlite" + f"databases/{get_language_iso(lang).upper()}LanguageData.sqlite" ) cursor = connection.cursor() @@ -139,11 +139,11 @@ def table_insert(word_type, keys): keys, ) - print(f"Database for {l} {maybe_over}written and connection made.") - for wt in language_word_type_dict[l]: - print(f"Creating {l} {wt} table...") + print(f"Database for {lang} {maybe_over}written and connection made.") + for wt in language_word_type_dict[lang]: + print(f"Creating {lang} {wt} table...") json_data = json.load( - open(f"{PATH_TO_ET_FILES}{l}/formatted_data/{wt}.json") + open(f"{PATH_TO_ET_FILES}{lang}/formatted_data/{wt}.json") ) if wt == "nouns": @@ -153,9 +153,9 @@ def table_insert(word_type, keys): keys = [row, json_data[row]["plural"], json_data[row]["form"]] table_insert(word_type=wt, keys=keys) - if "Scribe" not in json_data and l != "Russian": + if "Scribe" not in json_data and lang != "Russian": table_insert(word_type=wt, keys=["Scribe", "Scribes", ""]) - # elif "Писец" not in json_data and l == "Russian": + # elif "Писец" not in json_data and lang == "Russian": # table_insert(word_type=wt, keys=["Писец", "Писцы", ""]) connection.commit() @@ -214,7 +214,7 @@ def table_insert(word_type, keys): connection.commit() wt = "autocomplete_lexicon" - print(f"Creating {l} {wt} table...") + print(f"Creating {lang} {wt} table...") cols = ["word"] create_table(word_type=wt, cols=cols) @@ -306,7 +306,7 @@ def table_insert(word_type, keys): connection.commit() - print(f"{l} database created.") + print(f"{lang} database created.") else: - print(f"Skipping {l} database creation as no JSON data files were found.") + print(f"Skipping {lang} database creation as no JSON data files were found.") diff --git a/src/scribe_data/load/send_dbs_to_scribe.py b/src/scribe_data/load/send_dbs_to_scribe.py index 4da7b93a..082784c1 100644 --- a/src/scribe_data/load/send_dbs_to_scribe.py +++ b/src/scribe_data/load/send_dbs_to_scribe.py @@ -13,7 +13,7 @@ PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src" sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC) -from scribe_data.utils import ( +from scribe_data.utils import ( # noqa: E402 get_ios_data_path, get_language_from_iso, get_path_from_load_dir, From 6a9db2da77302555a6b0cbeefc7af2f394b0d5ca Mon Sep 17 00:00:00 2001 From: Andrew Tavis McAllister Date: Wed, 20 Mar 2024 03:29:36 +0100 Subject: [PATCH 10/10] #109 update changelog and fix final Ruff error --- CHANGELOG.md | 3 ++- .../languages/Portuguese/translations/translate_words.py | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 5689d33e..f2bce29c 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -21,9 +21,10 @@ Emojis for the following are chosen based on [gitmoji](https://gitmoji.dev/). ### ♻️ Code Refactoring +- Code formatting was shifted from [black](https://github.com/psf/black) to [Ruff](https://github.com/astral-sh/ruff). +- A Ruff based GitHub workflow was added to check the code formatting and lint the codebase on each pull request ([#109](https://github.com/scribe-org/Scribe-Data/issues/109)). - The `_update_files` directory was renamed `update_files` as these files are used in non-internal manners now ([#57](https://github.com/scribe-org/Scribe-Data/issues/57)). - A common function has been created to map Wikidata ids to noun genders ([#69](https://github.com/scribe-org/Scribe-Data/issues/69)). -- Code formatting was shifted from [black](https://github.com/psf/black) to [Ruff](https://github.com/astral-sh/ruff). ## Scribe-Data 3.2.2 diff --git a/src/scribe_data/extract_transform/languages/Portuguese/translations/translate_words.py b/src/scribe_data/extract_transform/languages/Portuguese/translations/translate_words.py index d170c943..884083d8 100644 --- a/src/scribe_data/extract_transform/languages/Portuguese/translations/translate_words.py +++ b/src/scribe_data/extract_transform/languages/Portuguese/translations/translate_words.py @@ -14,7 +14,7 @@ PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src" sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC) -from scribe_data.utils import translate_to_other_languages +from scribe_data.utils import translate_to_other_languages # noqa: E402 SRC_LANG = "Portuguese" translate_script_dir = os.path.dirname(os.path.abspath(__file__))