From aa22fd31db0484267b9d26c09f91500f7ad0871e Mon Sep 17 00:00:00 2001 From: Maxim Lysak Date: Tue, 15 Oct 2024 09:43:06 +0200 Subject: [PATCH] small corrections to pptx --- docling/backend/mspowerpoint_backend.py | 2 +- tests/data/powerpoint_sample.pptx | Bin 43304 -> 43285 bytes 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/docling/backend/mspowerpoint_backend.py b/docling/backend/mspowerpoint_backend.py index e2be8890..325386ef 100644 --- a/docling/backend/mspowerpoint_backend.py +++ b/docling/backend/mspowerpoint_backend.py @@ -201,7 +201,7 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB elif placeholder_type == PP_PLACEHOLDER.SUBTITLE: DocItemLabel.SECTION_HEADER - enum_list_item_value = 1 + enum_list_item_value = 0 doc.add_text( label=doc_label, diff --git a/tests/data/powerpoint_sample.pptx b/tests/data/powerpoint_sample.pptx index 78a54f9b97e8c5cbcd73df85182984e288991c4d..6e33aafc584ac6f623956a7ffb28f40e7dd041f4 100644 GIT binary patch delta 2587 zcmYk;c|6ox9|!Q6v5zd3>`61$LDnMK*A%kNG?T9E5fKp?j3f$I_}NC5YiFzzCPQS& zGVUN#WSgtF)MFX4-^TLD>v_EH`Rnukp6@^Byv{kVQ%-}V(;#)9PeDIop`Qy`L7*Tp z;Oi*_4m~4HLCYq)%kw1Dd6GB4!uTZQcZBH`RYA6&iV+QZ7IE5v&D9}}tO4;L*hO*P zZ@U_a`Z-hS&l*z*1B>@OTg;R0QxKIxkAv0gan09K{2i+WM~no5rSEQ`NL!R2+tU$V zrT2+-&LJb#-Bc%Ux}_{|$&q5$U>*!tKs(|_2?C-{BLnUQ@0G49C2&0w*ONDO8t;m1 z9NG^fQ`Ilm)(6Wg(7A12^NVWu-+cTriIyEveDNAdvUGCKq{OXGu|-kP)AyBvbO|2$ z%6{bbB_V?2egoMC)ds?iqol7rNYE7#WG68iCxQS<{j%n)gXKyFK?6SKNgwciu#X$n zk&TsEX-MCEzw{)#T5sjc0E)uPpoF&nJzUU3a3W{Ue;CeD(9$8SD7x}x=e!B~D@)4}ojW%RRywvI%x3nma{_%UXM>-Jr?Ee#8nz4bF~XR7Dge zEH$0#HqN4bI{$(B@mWubs9JVd8?~UFugQH|^4_>TZ)0t7E**5*C@Tr+F!}`iAptNDYz1lJDN_~Af;SS zF=Xu8>?cC$*so#tt(grMS~l@YX-$Lm+!bqKs!cAdJ_k{!xm}XYQF8mkBtbHb4^#7U zXdUH9&XB(7$ZR4wQ4Pxncyadk+l-ef#uLH#o$bEPJUDkmQQr*JjSAy{3z-WKbg{yF z`7Xm0yLs2`C1y8}$bBIywx^+#fdoV369rq4B^p@6Vj?Tf`e8>yX z$$KWqH>(TIvVl#;F5(C6zggAPBN6>?$Fl7p2URimO4^1N7lTiv;gWRf4|bNfafHN= z-#t8XbmgB%EK=xYKl$3>ExuQ}R>rl~@_wJ(RNB)H`ZhG2+lmRg>&pm8f=ye1$M6YL z4%~ouQZ(|9$@x}F^BgfnWrX{heiEXTEa=b(%6 zqw!}tvt}!^(dJ+g8~pXwN)u7xul2L!F}{IjmtCYs)vDj6FAf51;=PeEu*}lugDiZ{ zINfb1|ug2#d~?gXM+8{2Z{A! zbwnd2`=Oh*8iM(nxd~rXl#o*?qAbz6i!2Gmvs-&yz!L|7`c@$}9NU};`wO}H-V9YR zPK&Nhf&m1`d5NBQ6R&*w4#=m66fU8_+-%XZih3dw{O9$y7UoV<_*QNcc3hP7G-_hp zarS(ZtF~-wvGF{`n!MxDyP`w$L9EjVaO^>&Bfy))1Ioy@4wh zwfrRsw6rj8Q~ee0NX~A68=5dF)*&XvXw_^^O*tX&*$m~SBVOaH8h+>1^kqaEWnGD9 z)t^s=M}0Dkm#OHOu~2A7fY2SvY2CNk$-FfGx}BiwX~uGbrTh1P*sk7`!nKjF*4|!a ze_nxtF8QR>WQkb=W@bzWuL86Kt^IkTJc=fn9F)m#pS)QxRKojys=I@i@Eu~jmypz& zPrUoWX7V!ik(!sc+vtaENtapGSl1a}6OxHdbO?p@CAk+p{b_nU>fI@^>Qn~gts(O# z&jdvewcrIhc(*4Yb&e|^r#-dX-4#Em0T5_K`s0LGI1eP~QyC0Q$<@ zMzP0-`2}zPH<%w{zYYsqM2G(tx?Uz*4vgzm5r|#kz{aIAFIfc_7F5^q)C#aa^j*48 zY|eAZ`>LAHbfkA95?|L+d=R2Hc-dQ9zh6x&idbkT0<%qo*t|u=On82GYvnAHt4peg zPEU_ManX5L2N!;oT>4gR)f2(f!&Uc0Q~o-6@WbF`D^*fBN9uUr>HfG^{a5FAM|^Qa z&+s8q6rh#o%$0P8syYQV))gMcU{(z)aF*j-(4+!Zu6~RqELypW1-?v=zCebRJor7f z#p@jJ#&A5iYEheDes+N=yW`UszGBAn>|RJWc+R_{;&e@nPIqRJegF#wsGr~PJDUJUmoJhNvQ$cyaV$2>sgJ^E`h}yQjL7`^;l^6C z(;qr7fB@m4PWRVIchhui)&B8wY^iw1IY)kakSN7V38gQT23gi5wo0yOx9#EA?ttoZ zbKJrI{x@*v*+cS#07DL8AT&<{f)_rDe+ff@4|xc1CcwzEn^$`Gi|F`ph1VsuQ}A^Xh# z#}fdoP#F?odCb5=y4oI63g|7o2=TT%ip_T1fKm|x^1%Lx5k(r1M-E5v^I;4}9>oD9 z6u451fJCE!TGR!=qJ$qfC>8~O1=@=-kZE z5M#Hal2NG!#KQe3=9FrHZvexk7zonyu<&cUv=6s2tjrKH6A17<6ahxd5MTxXF4qGm z00!j-;BUZ_aw)N+w-EvYxwC;l{Gfl2BA~q-E_QS$z#tI*u;=8zr$Jy~zg&tvIpYna8m&7&;333i*udpzRq=Wh9Kl2NX@t)H|+TX1u7c|BrXXo z2*PpoofcWOv*)vj$k)K%|tsh2R#e9$VR3vwsdz`3x*Na}fKSmSI1m!}BF#XxPz zz8?YJEe3QYo*+5<=i{S{NDQh$p}fL1~X@@H$o$Tnu9R@RTkpSjthG4oO7Y0lJ*pl{fhmik9ynR9cPGdmEtC< zc_%Tdk7G`MzTKeWLyVI(hhDh%X%!wiW$PTCQfJZw?TnzyyxitMyst`27MuR`B5R0I z*4q?V^~_>axpmGJu7pWw4K5c{c-2*Kg6Eh^l*)!-DRDWQ|s zdUiaO(4%|9M_-*z@-63!i>BIB9>i%#tHst1kggFI6vz2(y(PuU%v=uvunxP)9%yLvgz2D7@ylHwm60u7vADQhI%Y^GiBW* zgkj4}VBGs@=ONI zMTqd*aet5WJ(YHhQ$wj5YNM$saWZMG^R~0&)X=nviZMsimeCI$c*J`0NX zYq0sKgX>ozzFX;Q`EM6^lf!=B zr9X4^E4RyzsXa?%J8(KaYQC>fT|KUDqqE64__uNHuu7xv1t}-&8~J~{m1lM{zZydD zOzJA6kP^0-{cw60v9A^JnZDfTj-Y93?P{AoS}y@H8OCcfyZoFf_j0eN3Qy~ej z2DO>#i3WL%Y%MG;!RR9$@XZf~WoEeAmfYML?&uC3-Gz2!XeMdqyZA4wrf+9=R#)z{ zo^;%IbN%iPuc9QqQSat@qmCW`ex%S7%ER+Kqy_se$h(MF+?BEl;DeP`VVQq^8-_qo`m~F>GFYM^2~-X&fOP4ZCWIGE$Vw z?tUcGEw8RU`f6Lz3j9qiFYv3&%V#?422o9YAbSb0y{UG% zN+Y_1@e>g$i5+!zVWxp6xOOUb5#5m!yJvtlQ(%Sk=l@}4#u%*b#rUH zg!6yAUSXEBGx?Cuvv(r5-^-^JD?(y}4VHw&^h8C;$UN@<=iew*-QJyfTPIDc*!+<8 z*Fp|(s??d4_{i|*YA4#w2$grkZhq*m)B{jyIRY5+#U=Pz5GiBsrK& zsl}dwBx9dX^_mE))pzwvJ;7ySzeaK@HnXV-EJ2B33*!4VzWG-*B2AkwY|8sYhFA^+ku2G2l?AQRsk6%!a zCBY@Up2+l*zSiatsPyZNIwIq7dwQivRVVX(CXAF>9r1mdscDT7z#WDhYoX~?f(w-t z+nOB|?+9#lc^2oSC(A9CU+{mDsXl4q&z2P;7|&a*vrV)qc=Aha%1EHXkBl9zea+8zHvB>M{hscz!5vXWAuWT8Aj;~nEsP^{gKG=)frt{+UHd_hY35v@W+9^qS=U` zC0Q#$I%U^e&%>iBdhB(vb!CaL(3si%!M8Sde3Vv^Cd_z^Dm_EmZg+L+2h??5JO6=m zKG^xGrARnLGIY-;tJ-`4Jw)+8U36&!6|;J~t1!Dg7%hzw9ZwFtq&H@vxpGp+E%u{^ z_NTG{!w@Qy@6WKX$71IYPE?_1Ffi_(n$Z1q&N$AVmTrH?sUm2@U^$c{JeaA{Ijl8u z@e;*(4m;>DO=({fJY0{@3-_dGzZ=p`&?>&7_!l}w&!!okG*!ARhxw_wDE8j2?VUL~ z%~{R=k-mX^b7}L?MrpZtov??V-x#|L20!Mx|s~Nzim`z?3^`Ls$y~JLEXE- zJlfnHin$(6ZHSKifofAZ9VH$E_==3%PGX`L44p{f021bTg3uP>jYZZ~W{SZs9c~d^ zra%2VxwI~yLWbdK2geVbt7m`N-XYN3!p=Kgxfz(OENii`v~1;ijGEIo#)OqL2A-VW z?c8W_3GT^oqo14Lf)z}=Y}h70Vy`GS&{6;glY!*|O9+P~ARq|^EDPa~S!p25R~pDI zRE0#yvAA@^Z5WHlB2~y2Wft!pQ5VVL&=Id`vnWeY1xo<71S{|kOy|Gvh!%?p*@Sz zB}fS102DZ=uo^ZUS?SPGx_6C51Q7{70In0Qz*ayF(FtPb#fnu+kq~EZ7E_Pt;lm={ zhZ|Teg+qLOkIp6s=#lfBv|7O27#U)^$7fT8*~a-A