From 40145b59b3c35e1dd19444b343ee0ab165c49d38 Mon Sep 17 00:00:00 2001
From: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
Date: Fri, 31 Jan 2025 16:03:28 +0100
Subject: [PATCH] fix(docx): merged cells not properly converted

Fix conversion issue of merged cells in Word tables leading to repeated text.
Simplify Word table conversion code.
Add docx file with several table formats for regression tests.

Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
---
 docling/backend/msword_backend.py             |  101 +-
 tests/data/docx/word_tables.docx              |  Bin 0 -> 16404 bytes
 .../docling_v2/word_tables.docx.html          |   75 +
 .../docling_v2/word_tables.docx.itxt          |   19 +
 .../docling_v2/word_tables.docx.json          | 2356 +++++++++++++++++
 .../docling_v2/word_tables.docx.md            |   44 +
 tests/test_backend_msword.py                  |    5 +-
 word_tables.html                              |   75 +
 8 files changed, 2612 insertions(+), 63 deletions(-)
 create mode 100644 tests/data/docx/word_tables.docx
 create mode 100644 tests/data/groundtruth/docling_v2/word_tables.docx.html
 create mode 100644 tests/data/groundtruth/docling_v2/word_tables.docx.itxt
 create mode 100644 tests/data/groundtruth/docling_v2/word_tables.docx.json
 create mode 100644 tests/data/groundtruth/docling_v2/word_tables.docx.md
 create mode 100644 word_tables.html

diff --git a/docling/backend/msword_backend.py b/docling/backend/msword_backend.py
index 02f8c86d..18b0418c 100644
--- a/docling/backend/msword_backend.py
+++ b/docling/backend/msword_backend.py
@@ -2,7 +2,7 @@ import logging
 import re
 from io import BytesIO
 from pathlib import Path
-from typing import Set, Union
+from typing import Optional, Set, Union
 
 import docx
 from docling_core.types.doc import (
@@ -14,6 +14,8 @@ from docling_core.types.doc import (
     TableCell,
     TableData,
 )
+from docx.oxml.table import CT_Tc
+from docx.table import Table, _Cell
 from lxml import etree
 from lxml.etree import XPath
 from PIL import Image, UnidentifiedImageError
@@ -449,30 +451,10 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
         return
 
     def handle_tables(self, element, docx_obj, doc):
-
-        # Function to check if a cell has a colspan (gridSpan)
-        def get_colspan(cell):
-            grid_span = cell._element.xpath("@w:gridSpan")
-            if grid_span:
-                return int(grid_span[0])  # Return the number of columns spanned
-            return 1  # Default is 1 (no colspan)
-
-        # Function to check if a cell has a rowspan (vMerge)
-        def get_rowspan(cell):
-            v_merge = cell._element.xpath("@w:vMerge")
-            if v_merge:
-                return v_merge[
-                    0
-                ]  # 'restart' indicates the beginning of a rowspan, others are continuation
-            return 1
-
-        table = docx.table.Table(element, docx_obj)
-
+        table: Table = Table(element, docx_obj)
         num_rows = len(table.rows)
-        num_cols = 0
-        for row in table.rows:
-            # Calculate the max number of columns
-            num_cols = max(num_cols, sum(get_colspan(cell) for cell in row.cells))
+        num_cols = len(table.columns)
+        _log.debug(f"Table grid with {num_rows} rows and {num_cols} columns")
 
         if num_rows == 1 and num_cols == 1:
             cell_element = table.rows[0].cells[0]
@@ -481,52 +463,47 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
             self.walk_linear(cell_element._element, docx_obj, doc)
             return
 
-        # Initialize the table grid
-        table_grid = [[None for _ in range(num_cols)] for _ in range(num_rows)]
-
-        data = TableData(num_rows=num_rows, num_cols=num_cols, table_cells=[])
-
+        data = TableData(num_rows=num_rows, num_cols=num_cols)
+        cell_set: set[CT_Tc] = set()
         for row_idx, row in enumerate(table.rows):
+            _log.debug(f"Row index {row_idx} with {len(row.cells)} populated cells")
             col_idx = 0
-            for c, cell in enumerate(row.cells):
-                row_span = get_rowspan(cell)
-                col_span = get_colspan(cell)
+            while col_idx < num_cols:
+                cell: _Cell = row.cells[col_idx]
+                _log.debug(
+                    f" col {col_idx} grid_span {cell.grid_span} grid_cols_before {row.grid_cols_before}"
+                )
+                if cell is None or cell._tc in cell_set:
+                    _log.debug(f"  skipped since repeated content")
+                    col_idx += cell.grid_span
+                    continue
+                else:
+                    cell_set.add(cell._tc)
 
-                cell_text = cell.text
-                # In case cell doesn't return text via docx library:
-                if len(cell_text) == 0:
-                    cell_xml = cell._element
+                spanned_idx = row_idx
+                spanned_tc: Optional[CT_Tc] = cell._tc
+                while spanned_tc == cell._tc:
+                    spanned_idx += 1
+                    spanned_tc = (
+                        table.rows[spanned_idx].cells[col_idx]._tc
+                        if spanned_idx < num_rows
+                        else None
+                    )
+                _log.debug(f"  spanned before row {spanned_idx}")
 
-                    texts = [""]
-                    for elem in cell_xml.iter():
-                        if elem.tag.endswith("t"):  # <w:t> tags that contain text
-                            if elem.text:
-                                texts.append(elem.text)
-                    # Join the collected text
-                    cell_text = " ".join(texts).strip()
-
-                # Find the next available column in the grid
-                while table_grid[row_idx][col_idx] is not None:
-                    col_idx += 1
-
-                # Fill the grid with the cell value, considering rowspan and colspan
-                for i in range(row_span if row_span == "restart" else 1):
-                    for j in range(col_span):
-                        table_grid[row_idx + i][col_idx + j] = ""
-
-                cell = TableCell(
-                    text=cell_text,
-                    row_span=row_span,
-                    col_span=col_span,
-                    start_row_offset_idx=row_idx,
-                    end_row_offset_idx=row_idx + row_span,
+                table_cell = TableCell(
+                    text=cell.text,
+                    row_span=spanned_idx - row_idx,
+                    col_span=cell.grid_span,
+                    start_row_offset_idx=row.grid_cols_before + row_idx,
+                    end_row_offset_idx=row.grid_cols_before + spanned_idx,
                     start_col_offset_idx=col_idx,
-                    end_col_offset_idx=col_idx + col_span,
+                    end_col_offset_idx=col_idx + cell.grid_span,
                     col_header=False,
                     row_header=False,
                 )
-
-                data.table_cells.append(cell)
+                data.table_cells.append(table_cell)
+                col_idx += cell.grid_span
 
         level = self.get_level()
         doc.add_table(data=data, parent=self.parents[level - 1])
diff --git a/tests/data/docx/word_tables.docx b/tests/data/docx/word_tables.docx
new file mode 100644
index 0000000000000000000000000000000000000000..1513796e09a42730b23a5faf788dc96c60995469
GIT binary patch
literal 16404
zcmeHuWpE}-uH|QDW^OaIncK|F%*@Qt<~B1kGuv%!Gcz+Y+ihm{dhVOqxpQZBH)8+3
zR}rO%%BrKR%92tkr6eZ_0*VR%2S5S<07AfK!Hks#5CHH63;;j@KmuzD+S)i7+c@be
zx!V~#YSX$|TYbp`1*XUW0DnIJKgWOL5vWfXwdtWp6n;p2Mu`2TY;crUMg<(slSHF%
z41wtZtnwB&*!JFm0xYi#6bo%dM9TEA!K5<aKfRJ>1%=e$O8OgvJIOCz$DHl!^5Pzi
zj}aExb^`qd|1hhs6?0oVmJ}-xJ#j;C+_)mNY({>DKbqPjAc`t6T7~3$BoltXD>~EG
zL;D6u@&>6LrECKP4!lkdGE98!B8!)e7!jt?vg53pX`)nsUOj5)iRbZLc7kWJT#Uo2
zza!pd6gDPrikxZ`#Hka36SMr+p#h>ISN+oPYELCC_vW7k)H18MTer%Er1j4$G(vPh
zu@h@)d6jCp>scQZ5JizdZCt{;t9S^Mv0K;x&O@01G%4O{k*m=*l!Cmq&=l+@E)mOh
zs8}<QT=)CQgQb;>u!0HuTOjlNUEYC>YOBf#^DO|w@vM(_y4Zs0B*dL{4j<mo!Rm|k
zBM1QS@c{ym`xlkOkH!9V@hN9ApBe}Asgk-5##WAWw11=jql*8H_3uxgUJ=)A(Mu1@
zcj5o$Kiw|B(v6ufLuWX(in$B{sVOdnvbtok`2NPVv;?eutS>q`GaEnk-7!PNc`HHt
z5<5v5F037D;Yp`g^QFxVkQmrj$l$hMw*#AgaBuQ9LM%=>;vcS#7B-0u9{U)QGTw!<
zPbGA}UkqbTL^(NUNK%)dWv{&WkmAjhlgco^U?HaI0a3;++!2J=GJ)j{ZNgiV%tR9t
z-Lp}v-KTUC-^3VcL3u}wZADK<nh|SI0gZjxHhuCvzq7bMG>{r97b=wQ#nVI!S>ydM
z>;Q|G^@32nUU%CTCqtY6=F>3!yM7c<|K3T50{}or005-VL2<QpFrqWEHFUQAv|E2O
zSf|>WwyW&u-nx1p{@V`=ZSl}Wct;#eU9fUet*w(`l_Vn8qcMpEsk)scq|3FQ)BRz1
zY^SgW;c@W8H?fDFTy2lZx;|s3{>2pP(!2e|gs+f6{$>nO<g@*6#oIm|U<7@3KP7tm
zNizDwk7h4PHQ;>SUN3y!u05GT2cvJyV&Mxy`cDqrzr8biip}nio7H3U3f<V<+4JC$
zUr}{P@<#1GQFOGXN99jDW=M%Z^5t~W#Jk~Esxb1hX>kRX>(ko2=BL(+BlC<VC-O03
z^9G1xzby^<Rt8SRvLLtqkb~f_4T3xm>!}p3iKUv4`Z6OPLp>iwvLZc`HBw^}H&sQl
zA&tC|NYWy{VlH#D4vtTkAK2!OL4HG@m^}PuhEKLhkW5gpWt<{oTU=-UOk@nK5&~5m
zet{=JvZ*1NvMX*0<;fgPJ`F1iO?g$kZCKkhy!r9dTNmw(%!BtstrKZH&G>6woyc^w
zQ=>$<Ydl%YsLq2!Z(akdL|*EgVVfGaRI=r7`U@)Q4Nr;yE<DAqSx*(NhqeH?))m6p
z17mtCP*zIssCCbz#MdSvNbH<ap^8m2g@7}z@VGH!m<^*faTe13o}htZL|+%spZ0T8
z>ZpuDw1&(Zw>G4vD?c^S92k`nGLA)Re&)hepcj$oT`x(1_6UEQ3;y0tV#y*-j&Rn8
zh8a26s*lYRQ0`njOtQhk3>qk;5SPO8Q=Lm^m5G$eqL{e_{gIJQzp0J4GXFiPFM2ex
z{@8rxeJSPCR5(jxXoS;q8M0F5>)2wj9VN|^r{~S!8<9-UYASW?X$QzM2n06Johqx*
zU2dlcuTzT!?^AMX>NBG|E=4^1E4BERHJ7`5wxqlN8g(zptKdB$QOQ0sUl50K%al?f
zqYaFRwP?|XSkJeomsvyrj6n{;SX|o?t!GAIt7}I>oKui4^4k@QSL$%wCRbps_&a`J
zSaZ+z(G6Yx9n-Vy^OI)11jOX*t$s||Nc9{_sW<I#)<z{nAv)|A)5PzHMv9ZUns=9w
z_kA_r6C?}}@G%tU;cDYfX~e#Bj`G$@4AE&SztN=1bd>(u&Ypb<zV+wEmn1K?tRi^N
z_LN(3%aKUvpe9||HpH&B{lFUBgpv1Mdah|Tua)?S+SioRp6GeCaGZ@ajdo;_p*Y8Y
zdX5!-Z6y|k{$2iIq6&t+Usf_xUj1;bI5IR6MrfoCR6hJF=0Mhrm_p{kPpJ>x-US^{
zIrUY4<i-cgcQbD0C3UOfa<_jS9Ujr@y+JWgW?9~VD|PStZ1S{XJ%#S*sxfK#>i%z{
z2R-uqor&yu*c;^Yj@Zp5Z$eeKstBiyxAkgl0PD!IinO}-&HdfIa=ufnE7y7ogz#qi
zD<sVP{>Ta|^AdOfO4u(PQdr3PSQOOA+JUJA4NDud1n!79phw92B~0xUZPZbgsr6iS
zIEn`l5iZMC@S!~T1h$pMFTd7{TF)M9SV}JE`2(5lv{!3>@f%N>%#lM|fLLti<n`uQ
z^sbH#>+31P>@LVmEZumYeoMGrMAiuefb6j+IkxS3QW`3d;Gao1({*U~CM3QtXj>PS
zfEQ*}Ft;b!mNy=Y)GY(Dx{JRAHCcn$YKBi;<A!9ukI4={*IO;}Mm`M_dU-_?1^c8t
zB{4$oN9n7FaF|)Az!tRgfB(U|Y#Ae=#%N(bB;G%SMeayTE{L~9xTw(UANL+Qmkq;=
z)cKv<e`4E+zBuYoxdhp$inx7j+E3Dh2Aip2Q!1Cq4SxbiZ;gMI-Oxaj3)0j7#@(*U
zRrG{7+)L&1hK69ZZD5tz5Ps#^D%><{OKWCa;)XBa1=or#x{C0(7RtRI5*?3~uy5VZ
zTfq#ek5CMAcASc&Z37?QmA*ia5SVIvs!8=nU-p!;B&AUkG2c>SQ>%f#KsN1-&)Y?A
zfUPbUHPW({#iNE=i9+xU%|fQ2Fr)_H^A%}o_eF_RzTF~49qRAY>!qUBw6GJ&ea&6~
zy=>P$CArZZi}Q{|SLUc30#RQI5I@`s+{KTM4kfnl=5yUulmlak3-ikgRwBrq5*pe@
zp;0HA@NY=<Wk9cvOI2~l7R!|0*sFJ{32UP9{74DssQp|UFpX}V7$JO0L^A`mnWMD~
zV%*WK5|1x6R_nm&?P{!KF=y%p$SgeR9g)qP7Uwa{uEj#bc3psj91vME(7leX)Icq&
z=3$qp1eha*+>vR9!46>4{@)gOXOV5(N!q5VLgf_hVL{mtvw^QZgsInRhDJYZ+%e&h
z_#T87HOK@j;_F~F`*x_UptgVETc@b44Gg5HY0=0}SGveu6$j%LU+8UuvqWC+)HJyy
z0^>5Q{;1xka|$X_tl~6|{%m7+4AI}>AVYVR&xpQk>1F>)u!3nSgtwetKAQr5c(W6M
zuv@`h=gqYYBZ4I<6bjZ3T~}qwKd}9<duh*?a`__-OCQD2O9kgWXJD&7<*OZG+mNUH
zuv5b+DsSYO1)Ag8u(~`1zY$m!&?~U-p;-1-+5Jk(H3h!l35tB3TlZr%_8!Lz9cU_u
znq8^b1&i>4$CWN5II!kVli9@33f+Oyd65MV2a7(J7;B^kqdE45aCVltuF}$IuN(3i
zLv_gcO2=ca^xR4bQs7`u{G|fM5n^0usZ<GWn!!kids$!H45ej-ZH;bO`8b)uZL5oQ
z5Jl=2(p1t3Q{A12QeQ20_p(%#V*}f<dI=gy>*jEpt+~SP$%ejEL~2|F*PIP9SPw=h
z_FZIC<fbkNXOwyH!*J>HJ*VnWR}xwQ^g7Gu3MkdNuDN9-L@1~_v*3=~^PV%0$b>P`
zXxDI9QXtu067Dib0JjO}T)-NgerFlsgX8HBk(3+XXN)go;Fss34$Sb)#F|ZO1}sce
z1HtoO7MFt=u-RG9Y8$TB1J|OTf9CVR0A;^84^E`ezm%^wEMCga%sn<5r+!P2^lv?@
zPqPv~I<1F927Ye4<0$TdChZiZg4fauYND@c$;WhcwPmgM+ICj^8JjEnW$XNaef77U
z?PIMVvk+Ey6p!_qS|1ymO|Qe6$b>yIT|o-s<`|Xk7}(CDliw0D5MO}<yLvkeb5te4
z-~b+9p^4?~rszXU1Ol-sexABRz`$*d`G7{|uts~(BEPTTz+H12_+Ypjo<on0-H@Cw
z@XX8g377clj}xboLxYNBg(QapT2tB|I9J+^YZS##8bvf`mCog=?12iMo5kV77Koe1
zID-(#*Zj=7MRfi(a~<kgN~gQv%RJ`;!|uPAB$CFF2*f8wrac)@dQ$lN+9iGm!RiGp
zjFaa}72X@7GbO@CLB-5ni>(hpNaK-RRdns<ktI0C^^VajnS1nUDnmmaL5@<Jv_QhJ
zTSqt5_C?x@q%`vw;1NlKAHLh2*9!8#ObxJufCdWpgQ>l}^gprKC7eQp`0D7r6m-{c
zy({=UP<edywj`dc`)Y-zN1alQu}7d+9+Yw?IF>T{gU|P&0i$+xr>8yajL{LyYdfw>
z!8h$_y7@_nHymaaNvw+-I%lKa1i;I-br%lfk%xy0oUDHc?18^QH&X3KY~W}3^cEZp
z7sWk2*#4Rio5Po(X=8lFa|>($rIpIeno;W`6AE+-GU=g<qtZfi&pkpJja~ZX64b<f
zl&w5_qY1(S%g)J4M7v$4*Z0Lm%;=Y*f<_!db~C(5kdV%|P?9LX&;zaAMoD)K0Wy>}
zBz@VE9-<ngqU~F2GDPw8_|8k+wDgw!`PPYSG227Zh1r#tEuoYEJ)+hJY`s2(Ep64Z
z*OeD%7IY}eqm1+Q0DJR|{7ioM1wvk1@`w`y$XX+m-J@leyb(5EAy6B*=02`EsCyBy
z?pIAPwWTid#F*kaUI;llFzzlDIEb@Qe`Fkcf^7YXt+e}Lrzji7ZGMsZoe1vlir$5I
z{3M`|dg+Pq$;2U|55x6_2;)VhfO~m6zrxz0-K@}?uXb9Cl|rn9E;Q$IAXnvlZRfN5
z@;pys;J3uz*4kxB6NiAJY`;aqk24n3`Y41V%6(+&!{-v0a`}Pb7r{az^By@&#WK*@
zhCb{2xqqoxE5O994uHb-Phcck=8_j?h<V42A=-IF^f1Zsq7;+eH)G#|zdn({XTq%n
zPe(a|K7@7s=5!PG4f|INpqtbicU3Kt=NmTYOcs09a<T&+{2M(3u?`=AAsoCKS2P5#
z4|p>owJI@^LDUX3BdyR33ul)H?x*e2l0B=5ei=b!gjE?YUs<#!$5J(>amR%p{8vz%
zyK<u6_$vs9Ri>*fyqpG0o;UZi4%nLwerMlIAD5Ha`VRd3OPMteie)!&J<LWA7~r(z
zzLh5`oPQ|>P3yjjtmE_jg38MHb~R$ZrxXW|;f98bRn%CWtbvW|F?i)}c@=I(&soKD
zkB2;pD4Ybrnc=yvA1s(vK*?uph5&`YmrRgnsRo;QNQGUj8&}lhM0wHq9`6braGNkS
z?*A$SHk>+k{a!66F11^@LJ`9qS3)D7KDx>-z58_V9eq9VoaZQh)5utUL2ZYfMtg&|
z=$UcS26qzGaU{A!dGcsaoJ)ngm}+@e_|`Zr%9xVj>xz_$?b{t|R@)KXb>g6Vy%_HY
z!GH4P7L4lTZ$CXahR-+%E&vkf4^QsD!X1D1=l&7;0Q!tVetLxey^o5x(NEX^GYS{@
z?w{gC!|5d_uxBMfxVrEL5XR>%p@tg2-R`Uw6aPJ>*K+AlmEt(*%ep$*9p)M_=TV$9
z<bZe-QSGrv<yMMcea??)scQKfj|wwZPg6(7Dr?F@Msn`XPbiOFVTvKRA;E|Pm)V#n
zN0Kfw+W&xgKn2`d$2r^~@z9k~21_oBzQ0NZ(e;ic!~*t_pwTvMW6Ph-7KDRGk&xH!
zBVz2BT|x~{(+Dh{UQ#ILP*_DWY>FV<kg-^fx~wa|zqCs~tGrXYHfxsly^&zx;%ACu
zlln~VRn*t^UntSpM-+szJl~%_gVO)*|0k3x1kHg10E1ru0JKkG_(N)(%#5v#>HeS$
zf5ZUPHN$b(P`&AHc|+V?xtQ)Bk#}f1SfyR!W7Z39<t;~<!dUY8<6I2|atdU<C{b5t
zg2A5`f)%jMatrC+7+|2<Uqd9)YD|qR(^iWDYAw~G3odZII1Z1F)ExKQUl@SML+qvE
zvv#!|@O<MaGq*`jzqv+{HAI0l`3}P(r{!eT39Px>UaY%Tb&V1UFaRs?Y$xkah6aey
zE&leTY9;IxQcM`C`DV<3T07kH9MP><%0}kA>8yE&xzh&(6;Zg7e)BDh$gV(%!^3jl
zkm!T-M|l*bey{`!BMGxh<K-NN?iHc_7HC`+@nP!pEU}X=yDuN@9^a(>UAE$8tHLHE
zl02biT>4R`7A-~!jVH}u&u(N6=RK#iZN4r@$WnhK=SkgkF_0Zc;@9z}gc_YG2Tt!O
z8oyf6@N=70%aq5s_kpT+8_O*=xHfR(=<#(HnU-C7y)70B4_KE=uSEhU9B>`~+Q9|*
zj&J9`-fH|7b3(R^YQk+AI5SnEHuw$_v>JL^E0b37_b-8!>4a6uvO~($!ne6c$dGd~
zVZda3)e6nvi;)*)!S?k6+$FX~fGDLXlGm#)+!-&^syd&{!h1&{lM3ppC^wH4JOSB^
z8DUwD(iYAVF~yzl-|vqO>qI*<ysn3r^9j0n;EDBPTcP8BQa>!ZW`Ddr8eSgCZoc33
zC%bUb?PkAS9@lMpf3V&4<lN22oAUCyKi`@9czy(eZJ1s*!SePn>}-K^fc-M3#xP3-
z;MFC^vxj}5mAs9Q=>?_2g85EO1ma}~235ZWK2*P}O*R_{_xOID#s5feAn8Zb^;_Nw
zfIvYCGE!mLQguM3sh=8fKfGKU(F(U6YJI+)lsq`9G{D_hiYqdd;~p-S+>1ym24E4v
zfK>0}=~?>u8z_r$<XFo$njVwSie(syhc&Mhu_es#I5{yg=k}L=x__%4U#RpOWM+z3
zGuxM%QlUQj-4{DbJu72aLj{p@L8N6d{HmondUlMNSwbSz2-6V9^fBp1#v`3zMqBlD
zZ$6cpP$OVEt06BjbF6Q9;rgJvb0b*f@>nlGx<iP8Tj*#i$a8CiWi)SqcnR0d{vo@E
zn}>V6)Sy$KJdvcaMp8tUhuyF-!dl9Ux+Sq1ub|3l2DKm&vkPLOEy@f+&~s0{-r2dI
z?)=XhBy}UoMs?#XW&>pw<RPOP;%IE>g9bJMr-abvVA=ljDm&`kBtaDtH<5u@jJt+p
zZ22@g!%q4I3S)Cc4e?FGhK62=8n(hykYDEy?%lK*dVT0>2Mfm9Rb%++Xoyi>U{((x
zkqv(k=|z13e`$33Dh&I8L1e*cUQ?)SV`H<@19w-MM?Ns@NR{(Zbsc-xKWmGx`SVcm
zY{{=$@ldHS?(C!p`j_@BEM@xkug(IjZes_SVZ}b+_7XE%s<aO;Va0}Qx|5V}j)T0Y
zn(#J1jv@-}Td=9;G*QdYuNR&NDKUaIL}uB)^MXg)dDDkv)~5v0zZNmaML#)#(;CU~
zf{647s|f`oN$oRdWfAT*pTzhlIH<E9+mzd|@FiUVW$v@NmG#X0N>c!Y<!!>TzSWAM
zsN0rnYx&vC{Z=WdR$l~7I310lkT!`kQxmIS%$y|5Rdu1IZb3)KE9{61d>?5iLLdjs
z2f9s-VGi5H6LKqhkL)dOaJ$N?V$Etb+N$fQ+H(`g;*dyeo5WEB>XRTupPf72JO8pP
z<(Ex0NET_mA@i(^8&a|P61ogr>@dj!TxtS6o5hsOo3dw^A>pNEOeNM+a402gbEG;<
zO}T3T>YmVjE7$mr3DXDYu8Fv-#Sv4myLoNY*wvJ%`rYA`G^=Y&p8td^Ei5cMonV-X
z{QJoAhq6B{>2a@_3v|?Q+<MTA9RI2!c!oYL>q3UU3iNqTnC3CnX4pV$wn4Z+oCrOy
z{Kznu|L;S%%oz^m*)!$TGf#%WT!$IU?3PIk1(3o5b$j0u#n~+0jWt4D1LZw0f90f>
zUyj<YnZL_qLKk@vCFa70VJ*UH0yU;B6*vcf<S?(3F_%w--0;9P=BwZ#{%%qD<)ULb
zyX(PtEn2Igjoi(m{8S#;z5N_$lmz8;!O^;gp*L(d>AnU2b})qy#PSOz!g5?>w$k~B
zcm4vxk03U9E?4GD0*U+(iu)f{=b^7PvMNuS9_yVq2Ru5-E6GL7Rf^gWiw!@$9WS2d
zZO?&{lH9kV+lw|If*ZDnEa%hSOO$`t<Gig**+#y0NC{Mmf8>J5FfZXmh{TI;Eoumc
zTDH99ED$gUHK>?!U6OA!eRCjXmkoNjxs6>lu%2r7`80C>ZU$Q;t#9E$0RRlxKZU^^
zjh&p#ZA=~iW&-O~R&91!5xwZ9eCThrL@`FAh%4$scAJKY&e6-MpQS<*qysSg3U=JW
z-#vm8%u1zyhPcLJq^B`CnlN+Wp7aiyPKd|~nN#%>g-qt@2?<d$psfmD-sy8^K@eNV
zbcKlXqj&oqZSC$?cX}?FreT8Ed<R7pFm2NU<up8@hIMWx#yw_IM*-3!MH2<bpJ&|@
z<7T~UN@x=aLQjx)gp8+11H+5d0*ypg7iBo8S5g=qS&ETTL8B3WI3%9ayly1?s?M4L
zxyu+7Mqk1Y-JaiYZ}lp=3|MoIE52y&Lowa3B@nfBTW?o-#Joznw&JTa60Z+}+Zn?U
z6V7J$;&&SJ0&i|rby7ma7qwxj@cfR=fBi#GCGK#R{QyrCGFA{jOm;UF&)sZu$?e{-
z9~RQi5m}h=%6W+whi7YMX=~lw$vavACmeQ#&`Zf^RIO$fa~8<(D?QohAR+m;O7mIb
zZNCSP65XV`urke~EOh8n7Zazr17nw8XbQPM_`iKQLn?9HE351LIeb4!GhA1<y5SNY
zwhUJPjx4gmM)_oxJuj4KSEY|HB9Ev6kcqEw@Q0;0X(5Yf22yAIk>l&ts2tL3c7u-L
zFCK_(f-e_~qwYV8^5cO^mSe;r7?lc6-aS%6uQjQMVz`YU$w$l)&QPJ7@|<XG>QvR8
z)0a@-3%u=nc5X{-%F+n7@MecFYnO3!ac{zhEXj6{9BMqo>eU)9rn=zOw>Ob0(Dykr
zLBHw9h3t|o4=_Z1CLi!fE?kRRvLWWFB3Fq67lU!L_FM^ZXL5S8-SxQXG9qYXxv3TK
zJ;B7aR-R4dfbA^r;<iXKA3rAC>0yweYkSJb*w=fxi=0K?U-2>*+j1S34So%}p0P8y
z+WE>H>f^JG3gP!+9NAj^@ryCxZorq8Lk`^9vUECv&s^Iz_*u)Gud@59Ds#jeB3i^c
z6k#Gb9;3kv`Et>cR9rfUn94>Wd(zw8S508dq7jw3?f7<;+gL>{I<X^_%iyKfldJ9}
zs+IKmJb2BgeMBd&r0Fff576_KYVDF4McO222U!lbi_)<#6hOVs02W{$Z-pvZFOU0F
zzj4>#cl>Wi-*kxvbZ=ygr1n+582O*H%&XT#VgTi@W`<TW!*c0AVmcx8vmXEK(-#kK
zhEQ5z1G%u7UPZRWd6aImo>^6}mGoGhTP<q0KCou8T<tcJr#~RzzxFmiOEi)?hw3=H
z!XWbjN<ekt;=Rnv{%uM#P!hzX){CZBaJ^&;A3h5^dOe||VQwiqvqvROH=*fvQU$*o
zMOl9jQ<@}(vZl}Dv=a25IdFLF(4G;IKQGN3H8Jbt$&x9woBnia(5$syVIux2>k9vh
z@wVUjA19B%gPN6<&&{*rCIA58A8TkwCwD93Kc<e)9W=*PR&?*p)HeiN-ZP$pM(U?H
zsdbstzTabHr8t~tOhN+amSIzIO1OuMbT%aXct7@l^ykNII20udCLk_74><www!H7J
z&WWJ9W=Vt8+^gxYc0Vzun2qE!HZsq=I@&$$TQK&(#EIj6CS;v)&v;%OX1~AxA|TM&
z?>7{<@dYV(Dpz)E{6!shSN`_Kr8R>#?4xIycAW{6R4LZoY2y0wHE!K@fli=NBc3R0
zP+W`aoB$se_rg5I3KCkAdMBnsf7?WOR$%4AlzBUZdOZ1xgKio>D2MwewT3Bmf%^o)
z_e6>|w9r{-6Gjlea`rK`3G{x1S3Rd_5>&Qq+#%WW0&w;oAY5SI-5BqF{S1o;FB|in
zJ|y_Vrk+q@kikkOaK3teeq5PR?-1UewXTtTB8{CbiKzQP8p@%#y-~6qqHe+oSRph$
zD3}XrsW8VCd9cSOWZbGA)r)h5q*(W!ST`kbuAjhA)bEo|NIrX_&&oC!Hq!*?p^shd
z_bACWeLZYW{H)@!;nmB|MV%+M*OR1@;aqNR!q@asw(dUe`Q<6UeC{~Lcey))<J#OZ
z2Me4J6+F$>Q4RuYp17iR+P$WCxW^SbUSPJPc$LzxZRdm3oA(8r%4%o`kF}d4i|BYZ
zQ!<%Y$K4f8JxDz4Z#1xFOseA^qfpZ$4jHbbiAtQ3g)v?qj~5LDk*{{W&M@y5?H0ek
zq@V7m1=O6Ps-q^DHVj|+9q}WFlYDn`(C~h$N79Ou?sg(Z=6kEudjK-zTE3cd&1a<F
zl*G7jub4h6+TxtJH`4UnJ#<}EA7jiip1jxTn8UF>qUs3C4=EZzm^H?o-b`kG%a|?M
zc>i4pYt&9?l%C*|m4!P>A#r_lwir_-ys_`0NW}g|0gHU~TUv{acKk!}hcvUb^}VD-
z-xi8gBcaiQJYsMU5nEIvo@1T!>9uM}P*JOeSz~!nl*|0oRTVbJva+DUN~@Vz50|l^
zJ@%Eo&^taWh}?@EwS~~GT3^sWjTuy=VJtNEU>+!Q6zSA7dlI|Iu38VOpW@Fc^gxlH
zvNY2hk*mBSP22YfP&Q3(#J)H-K0U6zXOkD7SI28`zj!@bx9`a<xvJ7Ez%H7`W(?{_
z&?C?&znXm^YtNq+8>!g~TSLggyfr)6|H9o>GFAk!Gi^o~yZJ&a6gKC@Mc3EEpck%(
zv>8e|c@#B!3nRUh22K*jo+a89aV?zMPfW{@ISn>$hOLn8cZQ%;0qXBmm*x>N&eD7n
zBs@D*_aY%gC!Py!*5R!K9ovWh<GXNAMC1iF@y2!U3p>HZS0LmJ+qi)5J<mtveIyHy
z4SoSwoy;-xyQ<*GCa*nRTVu)L%xUDZ=FGD2vu0VZMLV;}o1YDxpAFu#X1i}LI2fT)
zR|ge_jBPHivGn%v#!kF8JFQA8#-hZ>Y36p)j1I}McZ`V2XD(_tDK%#qbw><McML_!
zVjTx}j6y;*oHA^?cq@E2q*c(9@oiLGvcTn+1Cpm8*<|5RD~Z{6W8)?|^<gSRaL8wH
z;;a?|oI2J8m<0L_0NP#Z2Qq&bH3Xzrc_~w{Oddwv_0cQ5@|uBB3(l|ZXIVkFQ<C;Q
z^Rn0--?e5V=tj>)iM4A<^bwe^gWVL3r25k+p9IB+zYKS3S0<B0?`xC-F?g2HRd+!0
z#M~W$w8)5MJa3<!g`<VWcWuJ%oZR=mY$a9pGb*wVAZ&g63f*`eRQlEL<1usM<G9$r
z`iY3$>(;5hnmaL=WJ&l`KSo}R`Z}PmIMp88151!}qw{z-BbNHw-z8JtnOlONn{Xp$
zUPGFL%Pjn`A0o?#Yb=Ol!<HmmSbHeB#HQUB%edE*>BB#0S8-hw-K`Y%t(Ma0O<u;i
zuz|PfYBm6T?UC|_Q9J?ykvBK46^PAiH|v%s-l?#_HCJPnfb+nOa}#OS#V%gw<E$IC
z{<1;*qoW?w(YQZp4jV?TQJsWiwkY)#7yi$_8?QEeL6IGIied3KA7lHyNLZ+YaH!7{
z{PP5XI!N@rQa!@d+ohXj=o-*1&+p=r27;y6wLfrvd~iw{1l*vRB9EzNh<`Sbb$j+N
z-%9gg!0<rbv-M%dbQnzd-m*;<fN58%i`0tB#@M2K7v(|~LtAkkK;MzUOeza+;^qs(
zcHXhCt=#gAedWyb_?^~uy-bIICLc!<;a*lb4-!>xrPI1#N_GK?wI298Ai!xjF2p3s
zuy*zO?mDuC#<2CJ7RP_&^IKbuk=CfoEjpnbJ*O<yX_s(J-ryRaUez{<W-adhM6OJf
zT~Ifq?78r4sEJ$jwKiO4^|dBRu#-eVX!O$u-;(aAoAuopr;r=nIi?g&>h+fkgV{)0
zZQ%mqs~$@i+>*99kHhjtni`g?_{ykP1uhG|hG8o}=>+GpYXX+Bim+PW=&zQ}7^rIV
z_4bTJu`0fD3MF^(Ow-k1E;EQLHmYiK16_Ay2qBDQblRkpt+L6m!*!Pa#>-|e{066C
zU(_qB#Znuw9_>FHiDzK9Q6mT|!{-vhpE_g_B_ZyT(A_)?&%iFeOgOa+9R=BB1$Jh?
z48787^fhEBu2N(S_!QB<7{mp#UXBn{qlDN5+66K}&aXLMju2X-1QD1<3DOUpD#Ld>
z0Q$^cAn=}6Adup3r&+GR-ywg0rfhd@!{VGoDdYz_RRA9hnm|q<)nPdC{|ol{EEHM_
zClp#<P9QYllt3V&S#Fso+<M^uqr3lv8;KA6|L9Nqs#I2fg|;qxt2}Gr>wR!`%S`68
z(Z-0ifON26VtcJ2TqnkMM$Jpk-9T@tmMttu=%M(SQRs?;#(H03vQUnU=extSS8#MF
z&vmZkvks*D1gh_3kj9U+k&3T-(vm-i(w&7{%%My&>#9yIHGb&ZEhIV>(vF5JJlcUq
zw9Z86bJe7{8e8__wlsYe#R;0~)lOZe4}d=(84TK%{}Ol8csI?*i>JDn3>;8p$BZa*
z3aPCR)l4<ZfI1*Ia|$WATt^IBI34A?GYjocz5pL+vIM^`!jgcMWZ{~-g7i~K5R|+O
zD1vhyaU|6O^7D>VgjyLPaFWHto|ULw9(GrgB3y1pX^@<aQg1G-B#Tg&0^BDm8aJkr
z{#;3r!nBMq0cYOMA-E8mNUt;q@)P_6Wgak)`N>R*CBPvcyCQD-vlHrhM4(UfpE+tP
zjZ#VYTcGv^eX~I}!Q25i>P1Y>fD;U!kJCSE(qKfyRh5h>k8@nJ7$zByqEF!F?2*Gh
zgQVc8q<1qolQRoC`+TWg6-jHQR+#xH-$LwP8np_Mnl#S;n=F?OR3@#I{6Sn~CtN;1
z)xNw?<{yNVbG~U_0q0MI7{ci5=U9BUl7Eu8Op7&((#U@y!xAhu4RhlEAV$TXy;|h|
z3;D}Scx{o@1dH;mSBR;AzGq>$3SS%Z5AbGOI;Kr$km{PDK61}Jl;p4Zn6<r2=#8o(
zU2kHnneIRx4V+2Deh01qPvG^$P_8aT9>^p2^Y%#DpysTQT`WT{)R$F6YvNJm0=m2#
ztu%sh?1?_X*oK>Oqr#6^s?`P+YHqhWFc4>K_ys?I&887?SHsmda?MWVN`TvzD!rL;
zg3|E3Z~Tx@#e03f&w3SjBk1^4>0Q07#ibbGp;xA3Rix|aQl>mQr<lIsBVLxo?A#JL
zkvta5%b~+a?$R;8+V?)-ae$q4=W)<?aC5@#m@DT#Up=}!ToVEJWS9yxaUU}0)2^<S
z(Bn5jhbHi*(Q<86_oTtmFz%+GA$f_b;V)YJg}2+0{fnE0df6t6&{N-b;b!_Gj*hX(
z<3x{T*)VIbq%{tfj-sX8@hJCez~U_@RQ1e$(&Y(Eo_4@UZdNmkP7LL*NZ7<w7Nz>#
zw}6q;)Zmd)EK1{*;8>#lU0wx)yAPQ8)*5>zMxv++q}=M&YZN5WO;MpC^eo+TOe~NS
zw4c@tIjS|@23wD*gI!}0K$ehV>Zi<<xb3JP)(`=1zZLM{f7Q69Usw(=4w<pni1=5D
zJ%$FwUl3tS1oIjTEHQi(tGwS;^dWo{PbPfu3=~4TlzsG~Tx}x0Z$73Fchp~3t6%kg
zjCN9d6ozLjT)kr<G}noj5RBQB<{x8FE6YO0RjaN<fsJaWP;;H^s1Zcpdt>CKtxlV&
zpPf+y%6|N0nF1HpV30+ff9-8m0$uSBi7P9fR?W+Ke1}ORAqaV9(OmUOn+lA9+2s5d
zGr7CA!mC=H^mE1Z8aDt<uX7peu7Oi#Zj{W>*)gJFg9`eL<~+&OBJ%FG3lpC0o9lSw
zW4Fr(cEjA6&PirBNy*Kmih$+3A5G*j<gX%n4~1u+WmM_XGP@ND?pvYKs#!R^#15aJ
zK_%K)*m9!$$n8?{AZP74-d-OSpe`dzsVl_cq_Ugkr8IW~$(QG+pAEl(@#D~xE$eC=
z_CnFL@n5}}_c9@rFKVysPD3HI^IjxNdVNSi#6zh#mMOkn358b0b1Ry^9+Q-eL`McF
z%90$(U()4<lj~eODCUJRuuABB&lB=^PdzbEHD<l@jj+}&ue7EeSXd-ckXDnF7ol5{
zYhaT5qG&oMWFOHggErcqEQ^C=WTg0WroYr~JBZ}j?`_0!a%&~(Ib=`1lVaULwr=F%
zPOD|jp<qzc(WSES3B`C^&oUuGIUmX5e#<SZd}ZBnp=$d?dwmsDnbVV^8T2=59W7sO
zUxtm!iC{+8Xw~fmIjy~+DWUI6sE+Tc%l2wcpUAtKAFKb+#1m6CI}d~L*@)5w>XM0w
z^<A!b=p5;gAa|-guJ(BO@*dqgq@-kxOJS{c&UjSw{wd!pTL8=E=+=sIrBj4*Xm@F5
zpib!NoZ}hc*NL>b>iwnr#J1AhjdhIPDKtf|t`gsfeJomgZwW2~*<gc3EgQWiC5Xyw
zPE~GL+n1l+v)6WhGss9Kezm+DE^etw_re|)mK{=sbX-9N>~+mmQf$uZq7{?GPpX+1
ziJhbFB*%*mJ}Ajcp$J?ZLOii2@iwm1;i{%`*-fN`AYMjZ56U67R28t1nfRj{LntjL
z>94~}dmqI~pDwC%(D~AK4q;qYh?h&t#aQfJ{x@s*3Lgem$)w_EIdz9BjrolccLj0U
zp_S;1E|S`|_u9ey`9R`CwteR>JAPDMkta#~&E?}h2P|Z)zwTt%tc()~l@m0s4umNV
zsl(04E>dw4q{d-Y7fo+TDP$T2<1JgA-LJyp?K2!?XUpvmI-653*w(8%4D#iL(qXCH
zB!iy55HI>tU#zVg^NsLtp?I*9n>(TSlt+omwvFi8&9C|}kd;L5cb=Wju<FuP3->_q
zcEDl8ZfV*hqI4jUPdBsrqmnmbm52Q1Yo7?nox32Kxc(8`IA`&@WD)a__7gZUChq2w
zTqBL0SjZYlqNxH6d6#4tfe63X>7vU%;6+y;ney<1L&%x#Kn1b5W+GQpzW7&o6Mgeg
zvN8u8io_i15+?rRqHxBL(dyA);hLJWV9yC*K0KS`C20ZEz19weLAnE<!-MfGTZv%Y
z_Z>H{LFPH`tegW+t+ZDWCTIJvPKSE;bbFmD_v6-7gwmrgu)!~~F1KOEn_2RrnI^m_
zPnd}qCs=rwgfRDqijBN3`a@%4i$x#FCL+bN;fuDDzXIFZ&lN~iZQ1#wk!UNMU~y>A
z*ds`2$JxhY)^G$SVlUyIGD+d^OIz{`hzMF19h~a&Z~T9?_XnPR%h?6o?-^d#v5)Zj
zq*Os9UMs%O`uxXKYO;-IG272OG@o%~)PID5T#XGB{}e{fm|eH&`GN}AdLi`)4)Q4E
zV39OrQAbZ+r<QEw2K1DY0v7{mIm_~v%+I?Sx+=m?-Rxho>7F-8baZosl9A`@OCZzZ
z1~R8-czRWVN0ZoRVRfTo4-Et1s?(ld95}1=K7+I&__UBv3>c>!7Tk7>P&l`Nj;|qp
zrPr_JD^EqxZp}?wKC8mEn?t*Cph>)i;E<WcGRN`={~=8Hjf;5GoW5hY7+nc*x=BIh
zykP#98H<Lz`rek7TC|F&ER*@fn3)5Z`7jL!^(#GfQDsT4z%zw4QRTa@Ij^24*ckii
z3s!U`zo5xtY+g1KC#Ql_#s}IgP+t`WgE#v;QhLfpO~z&3>0stW$bi;?`mmNeC3;yl
z`*Fx1Oi_$&E7|R8{V^8Tky}ujX*G_2Ql)ZCPo-2(zXUeBckfeQ5tROB#Gtjgzd-+&
z(-opN-HNukYX}vyZ0ZGg>d0Ox%8JcR9f4pSuIqlf{}`uxwZk5O|EvQchX4SO|M7!N
zK1;Ne^bM?x{}$!ni(j?Lr$-FBP(9)NvdM<&V1~_7x?)XyHm*~#0$~>crQ*ehPflXn
zX(*^rX4ar@i$Q|<uFvD{9Zi6bph4=f&8JaEvK$g8glPj~-Y9wf-q?{D56Z;^rnnG7
z`VIO^ba}ch!gyZ&fZ&fiaP%}f@qMp$F~zOKDOiz4bny5>=QQ_Mr&T4UhnjNR=6RMI
z2jaxrLFQs75srw~AcIi_hbx088JJx|uaf|QJQlfOY?=B4Yz;$gdCpNVz<q`C=&V#4
z6Ir^JZ~flH51Kc~^kWrNd9|!*O!GUa6nKz53|}maVEqX9L9v?J$=H7SiPN!I;piLN
z@MEB`^)Es^Je9<40`AdZfplg1O|$rgxk>IS3?&`Nk}MJI$4IL{ib+1VsRk+LvrLyI
zz4#U#pJ}`cHIV|yGR8mr6NT*DcHRS2VfzVBx|3)rlp&`YlwBR-P4rVlrWDU;gqlqT
zehksqnJ#gq-AYkrPU)$7$ckZm@1Z$<0nU4iZFCr}R~n3mjs!JBX}E3UIQBR&GRu|r
zTQe|#z-b|IyQUaFbS+S><%?QuQoODc;52?!-i}4#t$T4U_H@|cm~H%kA=oHDk9kFv
zz8<wOdEXL~F?EtEJ{m#Yz4{`mwFhs%$AWp?5|vpW<te&v!{gOqxA%S#RiE)2FEl>3
zO{@fs^F1162JGkaXFbHfZxK-n5JtNEP4Pb^2<bDw<};~A&cW8sk<QT8;Sb^YtS9=P
zq?%8)iijJP`6H=D>{W2jYo}nlkV3o=y#^SHA1NfWCfER*caI_9om*z6C?UAdX29`a
z;&EmFR*+?ylRZI1l|)hj+3!F^ti57reTRsL80mWvm}NvzSOw5<Jr5T}Gfk7d-B|?K
zA*mi}0yFxW%3i;Rrd-%77-}yGA_r=Aq~cic98IaQXMYkOx%qbiG&iyo(|VMMvl21Z
zxF6AR_v0+>zFVl+ayi^H)Wb(ncU!3MD^sc+F%r)Wfx6Sy_659hQF^P5;^_}&OT76A
zs>#3JlnqNctJz~(P}?qN*yNI(FoGaAvvmAkw%w!z#_;HEwYVXSXw&>0!7C$dQsS0+
zHFN5`!G15W`|+F5!K488WHboyoiJ-%5s!j$JE7@bsrknie8ygeoh#utj2{$F+Q<j$
z*OqurA&H<}(EOWMN4$7=b+ux?$H_$PGKb$-#p0nona37Iucvvuaq>5)Z*7K&ZleAI
z_E&t-ZG8W<HvcZHB-~$my*`C?;!{`=|17Nfc6NW8=>A7mKLz#k$WZu0R@;cL5aiD*
z6(vRmHHqh-?YHDhfhLmL#i?;uYqf<wvf%s>`{1%&OxyEQYqn3?S(b5vN;0+g>&#<K
z%?cG)7Rp~s+fp+Q)uno<^fUUEy}MF$uXc%-zz-QnA{mIGaa7&o<2sF~N5D0aikTak
zOSQ~|^H}G`loOMh>>W1qq)!Vdl3+JcGy*MlAbQ$N+dL&dNR?$=o_8GGFZ%{_`xbCw
zV|bm?P0F+^{NN}OXrUBO(4XSAa{Vex7_L$DynyIvONLB~Vf4J9ev5z-qL2<vCOPWm
z<5#t_X@m(aUwhE_hgV4~?-p-WtU|DM02>(uI}kW=TmmmO1#()8cU3e27Lp5SLO38d
zg*sAPp@Y#~6fm_Ef!mPDh<*|P7OL)gkcn}qh&&@@JDk#KBdQZOw}uYGWyU99#IYwZ
z!fSS?L0tm!h+zB!fP6K-C+cx{uQaffU2yt9Xa`NcJ?z!(*XP_|t+0u71pD;zeh&P9
zi7XH>&F50-KbKGc@qhkA{zEafoaDbU_}603KVbp!pGlE_D*gN`@UK;H|Af|k=EnV7
zP26AM|C)OFPcQ)B^|=uIza?V+mD69-@&3uH4*ma-ocC82e@$ihCyN%mzq9yrV#8nI
zf8EUdC;Wl%AMpRZwfR@@UzfoD1iv%=9sHLC@n1Rob&d8<4%sY!=kPBpw!h;4)k^;p
w4FIgO0RaDIv;PYJ*Lm~L@Gy=)!T&ys%1MHKipSpyi(vrWpEE5t_usDm7pd?I_5c6?

literal 0
HcmV?d00001

diff --git a/tests/data/groundtruth/docling_v2/word_tables.docx.html b/tests/data/groundtruth/docling_v2/word_tables.docx.html
new file mode 100644
index 00000000..30f6e8d3
--- /dev/null
+++ b/tests/data/groundtruth/docling_v2/word_tables.docx.html
@@ -0,0 +1,75 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <link rel="icon" type="image/png"
+    href="https://ds4sd.github.io/docling/assets/logo.png"/>
+    <meta charset="UTF-8">
+    <title>
+    Powered by Docling
+    </title>
+    <style>
+    html {
+    background-color: LightGray;
+    }
+    body {
+    margin: 0 auto;
+    width:800px;
+    padding: 30px;
+    background-color: White;
+    font-family: Arial, sans-serif;
+    box-shadow: 10px 10px 10px grey;
+    }
+    figure{
+    display: block;
+    width: 100%;
+    margin: 0px;
+    margin-top: 10px;
+    margin-bottom: 10px;
+    }
+    img {
+    display: block;
+    margin: auto;
+    margin-top: 10px;
+    margin-bottom: 10px;
+    max-width: 640px;
+    max-height: 640px;
+    }
+    table {
+    min-width:500px;
+    background-color: White;
+    border-collapse: collapse;
+    cell-padding: 5px;
+    margin: auto;
+    margin-top: 10px;
+    margin-bottom: 10px;
+    }
+    th, td {
+    border: 1px solid black;
+    padding: 8px;
+    }
+    th {
+    font-weight: bold;
+    }
+    table tr:nth-child(even) td{
+    background-color: LightGray;
+    }
+    </style>
+    </head>
+<h2>Test with tables</h2>
+<p>A uniform table</p>
+<table><tbody><tr><td>Header 0.0</td><td>Header 0.1</td><td>Header 0.2</td></tr><tr><td>Cell 1.0</td><td>Cell 1.1</td><td>Cell 1.2</td></tr><tr><td>Cell 2.0</td><td>Cell 2.1</td><td>Cell 2.2</td></tr></tbody></table>
+<p></p>
+<p>A non-uniform table with horizontal spans</p>
+<table><tbody><tr><td>Header 0.0</td><td>Header 0.1</td><td>Header 0.2</td></tr><tr><td>Cell 1.0</td><td colspan="2">Merged Cell 1.1 1.2</td></tr><tr><td>Cell 2.0</td><td colspan="2">Merged Cell 2.1 2.2</td></tr></tbody></table>
+<p></p>
+<p>A non-uniform table with horizontal spans in inner columns</p>
+<table><tbody><tr><td>Header 0.0</td><td>Header 0.1</td><td>Header 0.2</td><td>Header 0.3</td></tr><tr><td>Cell 1.0</td><td colspan="2">Merged Cell 1.1 1.2</td><td>Cell 1.3</td></tr><tr><td>Cell 2.0</td><td colspan="2">Merged Cell 2.1 2.2</td><td>Cell 2.3</td></tr></tbody></table>
+<p></p>
+<p>A non-uniform table with vertical spans</p>
+<table><tbody><tr><td>Header 0.0</td><td>Header 0.1</td><td>Header 0.2</td></tr><tr><td>Cell 1.0</td><td rowspan="2">Merged Cell 1.1 2.1</td><td>Cell 1.2</td></tr><tr><td>Cell 2.0</td><td>Cell 2.2</td></tr><tr><td>Cell 3.0</td><td rowspan="2">Merged Cell 3.1 4.1</td><td>Cell 3.2</td></tr><tr><td>Cell 4.0</td><td>Cell 4.2</td></tr></tbody></table>
+<p></p>
+<p>A non-uniform table with all kinds of spans and empty cells</p>
+<table><tbody><tr><td>Header 0.0</td><td>Header 0.1</td><td>Header 0.2</td><td></td><td></td></tr><tr><td>Cell 1.0</td><td rowspan="2">Merged Cell 1.1 2.1</td><td>Cell 1.2</td><td></td><td></td></tr><tr><td>Cell 2.0</td><td>Cell 2.2</td><td></td><td></td></tr><tr><td>Cell 3.0</td><td rowspan="2">Merged Cell 3.1 4.1</td><td>Cell 3.2</td><td rowspan="3"></td><td></td></tr><tr><td>Cell 4.0</td><td>Cell 4.2</td><td rowspan="2">Merged Cell 4.4 5.4</td></tr><tr><td></td><td></td><td></td></tr><tr><td></td><td></td><td></td><td></td><td></td></tr><tr><td colspan="5"></td></tr><tr><td></td><td></td><td></td><td></td><td>Cell 8.4</td></tr></tbody></table>
+<p></p>
+<p></p>
+</html>
\ No newline at end of file
diff --git a/tests/data/groundtruth/docling_v2/word_tables.docx.itxt b/tests/data/groundtruth/docling_v2/word_tables.docx.itxt
new file mode 100644
index 00000000..dd42eb0a
--- /dev/null
+++ b/tests/data/groundtruth/docling_v2/word_tables.docx.itxt
@@ -0,0 +1,19 @@
+item-0 at level 0: unspecified: group _root_
+  item-1 at level 1: section: group header-0
+    item-2 at level 2: section_header: Test with tables
+      item-3 at level 3: paragraph: A uniform table
+      item-4 at level 3: table with [3x3]
+      item-5 at level 3: paragraph: 
+      item-6 at level 3: paragraph: A non-uniform table with horizontal spans
+      item-7 at level 3: table with [3x3]
+      item-8 at level 3: paragraph: 
+      item-9 at level 3: paragraph: A non-uniform table with horizontal spans in inner columns
+      item-10 at level 3: table with [3x4]
+      item-11 at level 3: paragraph: 
+      item-12 at level 3: paragraph: A non-uniform table with vertical spans
+      item-13 at level 3: table with [5x3]
+      item-14 at level 3: paragraph: 
+      item-15 at level 3: paragraph: A non-uniform table with all kinds of spans and empty cells
+      item-16 at level 3: table with [9x5]
+      item-17 at level 3: paragraph: 
+      item-18 at level 3: paragraph: 
\ No newline at end of file
diff --git a/tests/data/groundtruth/docling_v2/word_tables.docx.json b/tests/data/groundtruth/docling_v2/word_tables.docx.json
new file mode 100644
index 00000000..957a83c8
--- /dev/null
+++ b/tests/data/groundtruth/docling_v2/word_tables.docx.json
@@ -0,0 +1,2356 @@
+{
+  "schema_name": "DoclingDocument",
+  "version": "1.0.0",
+  "name": "word_tables",
+  "origin": {
+    "mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
+    "binary_hash": 8379738677198259833,
+    "filename": "word_tables.docx"
+  },
+  "furniture": {
+    "self_ref": "#/furniture",
+    "children": [],
+    "name": "_root_",
+    "label": "unspecified"
+  },
+  "body": {
+    "self_ref": "#/body",
+    "children": [
+      {
+        "$ref": "#/groups/0"
+      }
+    ],
+    "name": "_root_",
+    "label": "unspecified"
+  },
+  "groups": [
+    {
+      "self_ref": "#/groups/0",
+      "parent": {
+        "$ref": "#/body"
+      },
+      "children": [
+        {
+          "$ref": "#/texts/0"
+        }
+      ],
+      "name": "header-0",
+      "label": "section"
+    }
+  ],
+  "texts": [
+    {
+      "self_ref": "#/texts/0",
+      "parent": {
+        "$ref": "#/groups/0"
+      },
+      "children": [
+        {
+          "$ref": "#/texts/1"
+        },
+        {
+          "$ref": "#/tables/0"
+        },
+        {
+          "$ref": "#/texts/2"
+        },
+        {
+          "$ref": "#/texts/3"
+        },
+        {
+          "$ref": "#/tables/1"
+        },
+        {
+          "$ref": "#/texts/4"
+        },
+        {
+          "$ref": "#/texts/5"
+        },
+        {
+          "$ref": "#/tables/2"
+        },
+        {
+          "$ref": "#/texts/6"
+        },
+        {
+          "$ref": "#/texts/7"
+        },
+        {
+          "$ref": "#/tables/3"
+        },
+        {
+          "$ref": "#/texts/8"
+        },
+        {
+          "$ref": "#/texts/9"
+        },
+        {
+          "$ref": "#/tables/4"
+        },
+        {
+          "$ref": "#/texts/10"
+        },
+        {
+          "$ref": "#/texts/11"
+        }
+      ],
+      "label": "section_header",
+      "prov": [],
+      "orig": "Test with tables",
+      "text": "Test with tables",
+      "level": 1
+    },
+    {
+      "self_ref": "#/texts/1",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [],
+      "label": "paragraph",
+      "prov": [],
+      "orig": "A uniform table",
+      "text": "A uniform table"
+    },
+    {
+      "self_ref": "#/texts/2",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [],
+      "label": "paragraph",
+      "prov": [],
+      "orig": "",
+      "text": ""
+    },
+    {
+      "self_ref": "#/texts/3",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [],
+      "label": "paragraph",
+      "prov": [],
+      "orig": "A non-uniform table with horizontal spans",
+      "text": "A non-uniform table with horizontal spans"
+    },
+    {
+      "self_ref": "#/texts/4",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [],
+      "label": "paragraph",
+      "prov": [],
+      "orig": "",
+      "text": ""
+    },
+    {
+      "self_ref": "#/texts/5",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [],
+      "label": "paragraph",
+      "prov": [],
+      "orig": "A non-uniform table with horizontal spans in inner columns",
+      "text": "A non-uniform table with horizontal spans in inner columns"
+    },
+    {
+      "self_ref": "#/texts/6",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [],
+      "label": "paragraph",
+      "prov": [],
+      "orig": "",
+      "text": ""
+    },
+    {
+      "self_ref": "#/texts/7",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [],
+      "label": "paragraph",
+      "prov": [],
+      "orig": "A non-uniform table with vertical spans",
+      "text": "A non-uniform table with vertical spans"
+    },
+    {
+      "self_ref": "#/texts/8",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [],
+      "label": "paragraph",
+      "prov": [],
+      "orig": "",
+      "text": ""
+    },
+    {
+      "self_ref": "#/texts/9",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [],
+      "label": "paragraph",
+      "prov": [],
+      "orig": "A non-uniform table with all kinds of spans and empty cells",
+      "text": "A non-uniform table with all kinds of spans and empty cells"
+    },
+    {
+      "self_ref": "#/texts/10",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [],
+      "label": "paragraph",
+      "prov": [],
+      "orig": "",
+      "text": ""
+    },
+    {
+      "self_ref": "#/texts/11",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [],
+      "label": "paragraph",
+      "prov": [],
+      "orig": "",
+      "text": ""
+    }
+  ],
+  "pictures": [],
+  "tables": [
+    {
+      "self_ref": "#/tables/0",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [],
+      "label": "table",
+      "prov": [],
+      "captions": [],
+      "references": [],
+      "footnotes": [],
+      "data": {
+        "table_cells": [
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "Header 0.0",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "Header 0.1",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 2,
+            "end_col_offset_idx": 3,
+            "text": "Header 0.2",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "Cell 1.0",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "Cell 1.1",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 2,
+            "end_col_offset_idx": 3,
+            "text": "Cell 1.2",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 2,
+            "end_row_offset_idx": 3,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "Cell 2.0",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 2,
+            "end_row_offset_idx": 3,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "Cell 2.1",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 2,
+            "end_row_offset_idx": 3,
+            "start_col_offset_idx": 2,
+            "end_col_offset_idx": 3,
+            "text": "Cell 2.2",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          }
+        ],
+        "num_rows": 3,
+        "num_cols": 3,
+        "grid": [
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "Header 0.0",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "Header 0.1",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 2,
+              "end_col_offset_idx": 3,
+              "text": "Header 0.2",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            }
+          ],
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "Cell 1.0",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "Cell 1.1",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 2,
+              "end_col_offset_idx": 3,
+              "text": "Cell 1.2",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            }
+          ],
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 2,
+              "end_row_offset_idx": 3,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "Cell 2.0",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 2,
+              "end_row_offset_idx": 3,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "Cell 2.1",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 2,
+              "end_row_offset_idx": 3,
+              "start_col_offset_idx": 2,
+              "end_col_offset_idx": 3,
+              "text": "Cell 2.2",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            }
+          ]
+        ]
+      }
+    },
+    {
+      "self_ref": "#/tables/1",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [],
+      "label": "table",
+      "prov": [],
+      "captions": [],
+      "references": [],
+      "footnotes": [],
+      "data": {
+        "table_cells": [
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "Header 0.0",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "Header 0.1",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 2,
+            "end_col_offset_idx": 3,
+            "text": "Header 0.2",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "Cell 1.0",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 2,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 3,
+            "text": "Merged Cell 1.1 1.2",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 2,
+            "end_row_offset_idx": 3,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "Cell 2.0",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 2,
+            "start_row_offset_idx": 2,
+            "end_row_offset_idx": 3,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 3,
+            "text": "Merged Cell 2.1 2.2",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          }
+        ],
+        "num_rows": 3,
+        "num_cols": 3,
+        "grid": [
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "Header 0.0",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "Header 0.1",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 2,
+              "end_col_offset_idx": 3,
+              "text": "Header 0.2",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            }
+          ],
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "Cell 1.0",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 2,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 3,
+              "text": "Merged Cell 1.1 1.2",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 2,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 3,
+              "text": "Merged Cell 1.1 1.2",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            }
+          ],
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 2,
+              "end_row_offset_idx": 3,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "Cell 2.0",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 2,
+              "start_row_offset_idx": 2,
+              "end_row_offset_idx": 3,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 3,
+              "text": "Merged Cell 2.1 2.2",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 2,
+              "start_row_offset_idx": 2,
+              "end_row_offset_idx": 3,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 3,
+              "text": "Merged Cell 2.1 2.2",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            }
+          ]
+        ]
+      }
+    },
+    {
+      "self_ref": "#/tables/2",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [],
+      "label": "table",
+      "prov": [],
+      "captions": [],
+      "references": [],
+      "footnotes": [],
+      "data": {
+        "table_cells": [
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "Header 0.0",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "Header 0.1",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 2,
+            "end_col_offset_idx": 3,
+            "text": "Header 0.2",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 3,
+            "end_col_offset_idx": 4,
+            "text": "Header 0.3",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "Cell 1.0",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 2,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 3,
+            "text": "Merged Cell 1.1 1.2",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 3,
+            "end_col_offset_idx": 4,
+            "text": "Cell 1.3",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 2,
+            "end_row_offset_idx": 3,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "Cell 2.0",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 2,
+            "start_row_offset_idx": 2,
+            "end_row_offset_idx": 3,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 3,
+            "text": "Merged Cell 2.1 2.2",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 2,
+            "end_row_offset_idx": 3,
+            "start_col_offset_idx": 3,
+            "end_col_offset_idx": 4,
+            "text": "Cell 2.3",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          }
+        ],
+        "num_rows": 3,
+        "num_cols": 4,
+        "grid": [
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "Header 0.0",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "Header 0.1",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 2,
+              "end_col_offset_idx": 3,
+              "text": "Header 0.2",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 3,
+              "end_col_offset_idx": 4,
+              "text": "Header 0.3",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            }
+          ],
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "Cell 1.0",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 2,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 3,
+              "text": "Merged Cell 1.1 1.2",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 2,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 3,
+              "text": "Merged Cell 1.1 1.2",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 3,
+              "end_col_offset_idx": 4,
+              "text": "Cell 1.3",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            }
+          ],
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 2,
+              "end_row_offset_idx": 3,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "Cell 2.0",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 2,
+              "start_row_offset_idx": 2,
+              "end_row_offset_idx": 3,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 3,
+              "text": "Merged Cell 2.1 2.2",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 2,
+              "start_row_offset_idx": 2,
+              "end_row_offset_idx": 3,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 3,
+              "text": "Merged Cell 2.1 2.2",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 2,
+              "end_row_offset_idx": 3,
+              "start_col_offset_idx": 3,
+              "end_col_offset_idx": 4,
+              "text": "Cell 2.3",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            }
+          ]
+        ]
+      }
+    },
+    {
+      "self_ref": "#/tables/3",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [],
+      "label": "table",
+      "prov": [],
+      "captions": [],
+      "references": [],
+      "footnotes": [],
+      "data": {
+        "table_cells": [
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "Header 0.0",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "Header 0.1",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 2,
+            "end_col_offset_idx": 3,
+            "text": "Header 0.2",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "Cell 1.0",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 2,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 3,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "Merged Cell 1.1 2.1",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 2,
+            "end_col_offset_idx": 3,
+            "text": "Cell 1.2",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 2,
+            "end_row_offset_idx": 3,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "Cell 2.0",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 2,
+            "end_row_offset_idx": 3,
+            "start_col_offset_idx": 2,
+            "end_col_offset_idx": 3,
+            "text": "Cell 2.2",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 3,
+            "end_row_offset_idx": 4,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "Cell 3.0",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 2,
+            "col_span": 1,
+            "start_row_offset_idx": 3,
+            "end_row_offset_idx": 5,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "Merged Cell 3.1 4.1",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 3,
+            "end_row_offset_idx": 4,
+            "start_col_offset_idx": 2,
+            "end_col_offset_idx": 3,
+            "text": "Cell 3.2",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 4,
+            "end_row_offset_idx": 5,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "Cell 4.0",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 4,
+            "end_row_offset_idx": 5,
+            "start_col_offset_idx": 2,
+            "end_col_offset_idx": 3,
+            "text": "Cell 4.2",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          }
+        ],
+        "num_rows": 5,
+        "num_cols": 3,
+        "grid": [
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "Header 0.0",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "Header 0.1",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 2,
+              "end_col_offset_idx": 3,
+              "text": "Header 0.2",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            }
+          ],
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "Cell 1.0",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 2,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 3,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "Merged Cell 1.1 2.1",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 2,
+              "end_col_offset_idx": 3,
+              "text": "Cell 1.2",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            }
+          ],
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 2,
+              "end_row_offset_idx": 3,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "Cell 2.0",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 2,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 3,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "Merged Cell 1.1 2.1",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 2,
+              "end_row_offset_idx": 3,
+              "start_col_offset_idx": 2,
+              "end_col_offset_idx": 3,
+              "text": "Cell 2.2",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            }
+          ],
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 3,
+              "end_row_offset_idx": 4,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "Cell 3.0",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 2,
+              "col_span": 1,
+              "start_row_offset_idx": 3,
+              "end_row_offset_idx": 5,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "Merged Cell 3.1 4.1",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 3,
+              "end_row_offset_idx": 4,
+              "start_col_offset_idx": 2,
+              "end_col_offset_idx": 3,
+              "text": "Cell 3.2",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            }
+          ],
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 4,
+              "end_row_offset_idx": 5,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "Cell 4.0",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 2,
+              "col_span": 1,
+              "start_row_offset_idx": 3,
+              "end_row_offset_idx": 5,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "Merged Cell 3.1 4.1",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 4,
+              "end_row_offset_idx": 5,
+              "start_col_offset_idx": 2,
+              "end_col_offset_idx": 3,
+              "text": "Cell 4.2",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            }
+          ]
+        ]
+      }
+    },
+    {
+      "self_ref": "#/tables/4",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [],
+      "label": "table",
+      "prov": [],
+      "captions": [],
+      "references": [],
+      "footnotes": [],
+      "data": {
+        "table_cells": [
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "Header 0.0",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "Header 0.1",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 2,
+            "end_col_offset_idx": 3,
+            "text": "Header 0.2",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 3,
+            "end_col_offset_idx": 4,
+            "text": "",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 4,
+            "end_col_offset_idx": 5,
+            "text": "",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "Cell 1.0",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 2,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 3,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "Merged Cell 1.1 2.1",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 2,
+            "end_col_offset_idx": 3,
+            "text": "Cell 1.2",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 3,
+            "end_col_offset_idx": 4,
+            "text": "",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 4,
+            "end_col_offset_idx": 5,
+            "text": "",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 2,
+            "end_row_offset_idx": 3,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "Cell 2.0",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 2,
+            "end_row_offset_idx": 3,
+            "start_col_offset_idx": 2,
+            "end_col_offset_idx": 3,
+            "text": "Cell 2.2",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 2,
+            "end_row_offset_idx": 3,
+            "start_col_offset_idx": 3,
+            "end_col_offset_idx": 4,
+            "text": "",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 2,
+            "end_row_offset_idx": 3,
+            "start_col_offset_idx": 4,
+            "end_col_offset_idx": 5,
+            "text": "",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 3,
+            "end_row_offset_idx": 4,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "Cell 3.0",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 2,
+            "col_span": 1,
+            "start_row_offset_idx": 3,
+            "end_row_offset_idx": 5,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "Merged Cell 3.1 4.1",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 3,
+            "end_row_offset_idx": 4,
+            "start_col_offset_idx": 2,
+            "end_col_offset_idx": 3,
+            "text": "Cell 3.2",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 3,
+            "col_span": 1,
+            "start_row_offset_idx": 3,
+            "end_row_offset_idx": 6,
+            "start_col_offset_idx": 3,
+            "end_col_offset_idx": 4,
+            "text": "",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 3,
+            "end_row_offset_idx": 4,
+            "start_col_offset_idx": 4,
+            "end_col_offset_idx": 5,
+            "text": "",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 4,
+            "end_row_offset_idx": 5,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "Cell 4.0",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 4,
+            "end_row_offset_idx": 5,
+            "start_col_offset_idx": 2,
+            "end_col_offset_idx": 3,
+            "text": "Cell 4.2",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 2,
+            "col_span": 1,
+            "start_row_offset_idx": 4,
+            "end_row_offset_idx": 6,
+            "start_col_offset_idx": 4,
+            "end_col_offset_idx": 5,
+            "text": "Merged Cell 4.4 5.4",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 5,
+            "end_row_offset_idx": 6,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 5,
+            "end_row_offset_idx": 6,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 5,
+            "end_row_offset_idx": 6,
+            "start_col_offset_idx": 2,
+            "end_col_offset_idx": 3,
+            "text": "",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 6,
+            "end_row_offset_idx": 7,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 6,
+            "end_row_offset_idx": 7,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 6,
+            "end_row_offset_idx": 7,
+            "start_col_offset_idx": 2,
+            "end_col_offset_idx": 3,
+            "text": "",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 6,
+            "end_row_offset_idx": 7,
+            "start_col_offset_idx": 3,
+            "end_col_offset_idx": 4,
+            "text": "",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 6,
+            "end_row_offset_idx": 7,
+            "start_col_offset_idx": 4,
+            "end_col_offset_idx": 5,
+            "text": "",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 5,
+            "start_row_offset_idx": 7,
+            "end_row_offset_idx": 8,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 5,
+            "text": "",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 8,
+            "end_row_offset_idx": 9,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 8,
+            "end_row_offset_idx": 9,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 8,
+            "end_row_offset_idx": 9,
+            "start_col_offset_idx": 2,
+            "end_col_offset_idx": 3,
+            "text": "",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 8,
+            "end_row_offset_idx": 9,
+            "start_col_offset_idx": 3,
+            "end_col_offset_idx": 4,
+            "text": "",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 8,
+            "end_row_offset_idx": 9,
+            "start_col_offset_idx": 4,
+            "end_col_offset_idx": 5,
+            "text": "Cell 8.4",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false
+          }
+        ],
+        "num_rows": 9,
+        "num_cols": 5,
+        "grid": [
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "Header 0.0",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "Header 0.1",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 2,
+              "end_col_offset_idx": 3,
+              "text": "Header 0.2",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 3,
+              "end_col_offset_idx": 4,
+              "text": "",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 4,
+              "end_col_offset_idx": 5,
+              "text": "",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            }
+          ],
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "Cell 1.0",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 2,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 3,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "Merged Cell 1.1 2.1",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 2,
+              "end_col_offset_idx": 3,
+              "text": "Cell 1.2",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 3,
+              "end_col_offset_idx": 4,
+              "text": "",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 4,
+              "end_col_offset_idx": 5,
+              "text": "",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            }
+          ],
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 2,
+              "end_row_offset_idx": 3,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "Cell 2.0",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 2,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 3,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "Merged Cell 1.1 2.1",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 2,
+              "end_row_offset_idx": 3,
+              "start_col_offset_idx": 2,
+              "end_col_offset_idx": 3,
+              "text": "Cell 2.2",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 2,
+              "end_row_offset_idx": 3,
+              "start_col_offset_idx": 3,
+              "end_col_offset_idx": 4,
+              "text": "",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 2,
+              "end_row_offset_idx": 3,
+              "start_col_offset_idx": 4,
+              "end_col_offset_idx": 5,
+              "text": "",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            }
+          ],
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 3,
+              "end_row_offset_idx": 4,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "Cell 3.0",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 2,
+              "col_span": 1,
+              "start_row_offset_idx": 3,
+              "end_row_offset_idx": 5,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "Merged Cell 3.1 4.1",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 3,
+              "end_row_offset_idx": 4,
+              "start_col_offset_idx": 2,
+              "end_col_offset_idx": 3,
+              "text": "Cell 3.2",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 3,
+              "col_span": 1,
+              "start_row_offset_idx": 3,
+              "end_row_offset_idx": 6,
+              "start_col_offset_idx": 3,
+              "end_col_offset_idx": 4,
+              "text": "",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 3,
+              "end_row_offset_idx": 4,
+              "start_col_offset_idx": 4,
+              "end_col_offset_idx": 5,
+              "text": "",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            }
+          ],
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 4,
+              "end_row_offset_idx": 5,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "Cell 4.0",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 2,
+              "col_span": 1,
+              "start_row_offset_idx": 3,
+              "end_row_offset_idx": 5,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "Merged Cell 3.1 4.1",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 4,
+              "end_row_offset_idx": 5,
+              "start_col_offset_idx": 2,
+              "end_col_offset_idx": 3,
+              "text": "Cell 4.2",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 3,
+              "col_span": 1,
+              "start_row_offset_idx": 3,
+              "end_row_offset_idx": 6,
+              "start_col_offset_idx": 3,
+              "end_col_offset_idx": 4,
+              "text": "",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 2,
+              "col_span": 1,
+              "start_row_offset_idx": 4,
+              "end_row_offset_idx": 6,
+              "start_col_offset_idx": 4,
+              "end_col_offset_idx": 5,
+              "text": "Merged Cell 4.4 5.4",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            }
+          ],
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 5,
+              "end_row_offset_idx": 6,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 5,
+              "end_row_offset_idx": 6,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 5,
+              "end_row_offset_idx": 6,
+              "start_col_offset_idx": 2,
+              "end_col_offset_idx": 3,
+              "text": "",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 3,
+              "col_span": 1,
+              "start_row_offset_idx": 3,
+              "end_row_offset_idx": 6,
+              "start_col_offset_idx": 3,
+              "end_col_offset_idx": 4,
+              "text": "",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 2,
+              "col_span": 1,
+              "start_row_offset_idx": 4,
+              "end_row_offset_idx": 6,
+              "start_col_offset_idx": 4,
+              "end_col_offset_idx": 5,
+              "text": "Merged Cell 4.4 5.4",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            }
+          ],
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 6,
+              "end_row_offset_idx": 7,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 6,
+              "end_row_offset_idx": 7,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 6,
+              "end_row_offset_idx": 7,
+              "start_col_offset_idx": 2,
+              "end_col_offset_idx": 3,
+              "text": "",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 6,
+              "end_row_offset_idx": 7,
+              "start_col_offset_idx": 3,
+              "end_col_offset_idx": 4,
+              "text": "",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 6,
+              "end_row_offset_idx": 7,
+              "start_col_offset_idx": 4,
+              "end_col_offset_idx": 5,
+              "text": "",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            }
+          ],
+          [
+            {
+              "row_span": 1,
+              "col_span": 5,
+              "start_row_offset_idx": 7,
+              "end_row_offset_idx": 8,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 5,
+              "text": "",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 5,
+              "start_row_offset_idx": 7,
+              "end_row_offset_idx": 8,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 5,
+              "text": "",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 5,
+              "start_row_offset_idx": 7,
+              "end_row_offset_idx": 8,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 5,
+              "text": "",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 5,
+              "start_row_offset_idx": 7,
+              "end_row_offset_idx": 8,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 5,
+              "text": "",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 5,
+              "start_row_offset_idx": 7,
+              "end_row_offset_idx": 8,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 5,
+              "text": "",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            }
+          ],
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 8,
+              "end_row_offset_idx": 9,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 8,
+              "end_row_offset_idx": 9,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 8,
+              "end_row_offset_idx": 9,
+              "start_col_offset_idx": 2,
+              "end_col_offset_idx": 3,
+              "text": "",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 8,
+              "end_row_offset_idx": 9,
+              "start_col_offset_idx": 3,
+              "end_col_offset_idx": 4,
+              "text": "",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 8,
+              "end_row_offset_idx": 9,
+              "start_col_offset_idx": 4,
+              "end_col_offset_idx": 5,
+              "text": "Cell 8.4",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false
+            }
+          ]
+        ]
+      }
+    }
+  ],
+  "key_value_items": [],
+  "pages": {}
+}
\ No newline at end of file
diff --git a/tests/data/groundtruth/docling_v2/word_tables.docx.md b/tests/data/groundtruth/docling_v2/word_tables.docx.md
new file mode 100644
index 00000000..90123c3e
--- /dev/null
+++ b/tests/data/groundtruth/docling_v2/word_tables.docx.md
@@ -0,0 +1,44 @@
+## Test with tables
+
+A uniform table
+
+| Header 0.0   | Header 0.1   | Header 0.2   |
+|--------------|--------------|--------------|
+| Cell 1.0     | Cell 1.1     | Cell 1.2     |
+| Cell 2.0     | Cell 2.1     | Cell 2.2     |
+
+A non-uniform table with horizontal spans
+
+| Header 0.0   | Header 0.1          | Header 0.2          |
+|--------------|---------------------|---------------------|
+| Cell 1.0     | Merged Cell 1.1 1.2 | Merged Cell 1.1 1.2 |
+| Cell 2.0     | Merged Cell 2.1 2.2 | Merged Cell 2.1 2.2 |
+
+A non-uniform table with horizontal spans in inner columns
+
+| Header 0.0   | Header 0.1          | Header 0.2          | Header 0.3   |
+|--------------|---------------------|---------------------|--------------|
+| Cell 1.0     | Merged Cell 1.1 1.2 | Merged Cell 1.1 1.2 | Cell 1.3     |
+| Cell 2.0     | Merged Cell 2.1 2.2 | Merged Cell 2.1 2.2 | Cell 2.3     |
+
+A non-uniform table with vertical spans
+
+| Header 0.0   | Header 0.1          | Header 0.2   |
+|--------------|---------------------|--------------|
+| Cell 1.0     | Merged Cell 1.1 2.1 | Cell 1.2     |
+| Cell 2.0     | Merged Cell 1.1 2.1 | Cell 2.2     |
+| Cell 3.0     | Merged Cell 3.1 4.1 | Cell 3.2     |
+| Cell 4.0     | Merged Cell 3.1 4.1 | Cell 4.2     |
+
+A non-uniform table with all kinds of spans and empty cells
+
+| Header 0.0   | Header 0.1          | Header 0.2   |    |                     |
+|--------------|---------------------|--------------|----|---------------------|
+| Cell 1.0     | Merged Cell 1.1 2.1 | Cell 1.2     |    |                     |
+| Cell 2.0     | Merged Cell 1.1 2.1 | Cell 2.2     |    |                     |
+| Cell 3.0     | Merged Cell 3.1 4.1 | Cell 3.2     |    |                     |
+| Cell 4.0     | Merged Cell 3.1 4.1 | Cell 4.2     |    | Merged Cell 4.4 5.4 |
+|              |                     |              |    | Merged Cell 4.4 5.4 |
+|              |                     |              |    |                     |
+|              |                     |              |    |                     |
+|              |                     |              |    | Cell 8.4            |
\ No newline at end of file
diff --git a/tests/test_backend_msword.py b/tests/test_backend_msword.py
index 9edcb3e6..86bd837d 100644
--- a/tests/test_backend_msword.py
+++ b/tests/test_backend_msword.py
@@ -69,7 +69,6 @@ def verify_export(pred_text: str, gtfile: str):
         with open(gtfile, "r") as fr:
             true_text = fr.read()
 
-        assert pred_text == true_text, "pred_itxt==true_itxt"
         return pred_text == true_text
 
 
@@ -101,3 +100,7 @@ def test_e2e_docx_conversions():
 
         pred_json: str = json.dumps(doc.export_to_dict(), indent=2)
         assert verify_export(pred_json, str(gt_path) + ".json"), "export to json"
+
+        if docx_path.name == "word_tables.docx":
+            pred_html: str = doc.export_to_html()
+            assert verify_export(pred_html, str(gt_path) + ".html"), "export to html"
diff --git a/word_tables.html b/word_tables.html
new file mode 100644
index 00000000..30f6e8d3
--- /dev/null
+++ b/word_tables.html
@@ -0,0 +1,75 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <link rel="icon" type="image/png"
+    href="https://ds4sd.github.io/docling/assets/logo.png"/>
+    <meta charset="UTF-8">
+    <title>
+    Powered by Docling
+    </title>
+    <style>
+    html {
+    background-color: LightGray;
+    }
+    body {
+    margin: 0 auto;
+    width:800px;
+    padding: 30px;
+    background-color: White;
+    font-family: Arial, sans-serif;
+    box-shadow: 10px 10px 10px grey;
+    }
+    figure{
+    display: block;
+    width: 100%;
+    margin: 0px;
+    margin-top: 10px;
+    margin-bottom: 10px;
+    }
+    img {
+    display: block;
+    margin: auto;
+    margin-top: 10px;
+    margin-bottom: 10px;
+    max-width: 640px;
+    max-height: 640px;
+    }
+    table {
+    min-width:500px;
+    background-color: White;
+    border-collapse: collapse;
+    cell-padding: 5px;
+    margin: auto;
+    margin-top: 10px;
+    margin-bottom: 10px;
+    }
+    th, td {
+    border: 1px solid black;
+    padding: 8px;
+    }
+    th {
+    font-weight: bold;
+    }
+    table tr:nth-child(even) td{
+    background-color: LightGray;
+    }
+    </style>
+    </head>
+<h2>Test with tables</h2>
+<p>A uniform table</p>
+<table><tbody><tr><td>Header 0.0</td><td>Header 0.1</td><td>Header 0.2</td></tr><tr><td>Cell 1.0</td><td>Cell 1.1</td><td>Cell 1.2</td></tr><tr><td>Cell 2.0</td><td>Cell 2.1</td><td>Cell 2.2</td></tr></tbody></table>
+<p></p>
+<p>A non-uniform table with horizontal spans</p>
+<table><tbody><tr><td>Header 0.0</td><td>Header 0.1</td><td>Header 0.2</td></tr><tr><td>Cell 1.0</td><td colspan="2">Merged Cell 1.1 1.2</td></tr><tr><td>Cell 2.0</td><td colspan="2">Merged Cell 2.1 2.2</td></tr></tbody></table>
+<p></p>
+<p>A non-uniform table with horizontal spans in inner columns</p>
+<table><tbody><tr><td>Header 0.0</td><td>Header 0.1</td><td>Header 0.2</td><td>Header 0.3</td></tr><tr><td>Cell 1.0</td><td colspan="2">Merged Cell 1.1 1.2</td><td>Cell 1.3</td></tr><tr><td>Cell 2.0</td><td colspan="2">Merged Cell 2.1 2.2</td><td>Cell 2.3</td></tr></tbody></table>
+<p></p>
+<p>A non-uniform table with vertical spans</p>
+<table><tbody><tr><td>Header 0.0</td><td>Header 0.1</td><td>Header 0.2</td></tr><tr><td>Cell 1.0</td><td rowspan="2">Merged Cell 1.1 2.1</td><td>Cell 1.2</td></tr><tr><td>Cell 2.0</td><td>Cell 2.2</td></tr><tr><td>Cell 3.0</td><td rowspan="2">Merged Cell 3.1 4.1</td><td>Cell 3.2</td></tr><tr><td>Cell 4.0</td><td>Cell 4.2</td></tr></tbody></table>
+<p></p>
+<p>A non-uniform table with all kinds of spans and empty cells</p>
+<table><tbody><tr><td>Header 0.0</td><td>Header 0.1</td><td>Header 0.2</td><td></td><td></td></tr><tr><td>Cell 1.0</td><td rowspan="2">Merged Cell 1.1 2.1</td><td>Cell 1.2</td><td></td><td></td></tr><tr><td>Cell 2.0</td><td>Cell 2.2</td><td></td><td></td></tr><tr><td>Cell 3.0</td><td rowspan="2">Merged Cell 3.1 4.1</td><td>Cell 3.2</td><td rowspan="3"></td><td></td></tr><tr><td>Cell 4.0</td><td>Cell 4.2</td><td rowspan="2">Merged Cell 4.4 5.4</td></tr><tr><td></td><td></td><td></td></tr><tr><td></td><td></td><td></td><td></td><td></td></tr><tr><td colspan="5"></td></tr><tr><td></td><td></td><td></td><td></td><td>Cell 8.4</td></tr></tbody></table>
+<p></p>
+<p></p>
+</html>
\ No newline at end of file