ci: switch to windows 2025 (#149)

Signed-off-by: Michele Dolfi <[email protected]>
Signed-off-by: Peter Staar <[email protected]>
Co-authored-by: Peter Staar <[email protected]>

Author: dolfim-ibm

.github/workflows/wheels.yml

@@ -61,7 +61,7 @@ jobs:
             min_macos_version: "14"
             platform_id: "macosx_arm64"
 
-          - name: "windows-latest"
+          - name: "windows-2025"
             platform: "windows"
             platform_id: "win_amd64"      
 

pyproject.toml

@@ -27,7 +27,7 @@ dependencies = [
     "tabulate>=0.9.0,<1.0.0",
     "pillow>=10.0.0,<12.0.0",
     "pydantic>=2.0.0",
-    "docling-core>=2.29.0",
+    "docling-core>=2.44.1",
     "pywin32>=305; sys_platform == 'win32'",
 ]
 [project.urls]

tests/data/groundtruth/cropbox_versus_mediabox_01.pdf.page_no_1.py.json.char.txt

@@ -1,12 +1,12 @@
-(322.16, 287.46) (386.71, 287.46) (386.71, 297.38) (322.16, 297.38)      /T1_3 KARLSTAD sofa  
-(322.16, 265.98) (387.82, 252.69) (387.82, 292.99) (322.16, 289.48)      /T1_3 $ 599
-(430.99, 010.48) (524.75, 010.48) (524.75, 022.88) (430.99, 022.88)      /T1_3 www.IKEA-USA.com
-(031.03, 538.21) (347.92, 538.21) (347.92, 546.97) (031.03, 546.97)      /T1_4 ALL CATALOG PRICES ARE VALID UNTIL JUNE 30, 2008
-(031.03, 025.16) (112.83, 025.16) (112.83, 035.08) (031.03, 035.08)      /T1_3 KARLSTAD sofa $599
-(113.09, 025.77) (148.52, 025.77) (148.52, 032.77) (113.09, 032.77)      /T1_1  See p. 4  
-(031.03, 016.66) (203.67, 016.66) (203.67, 026.58) (031.03, 026.58)      /T1_3 LINNARP bookcase with glass doors $349/ea
-(203.99, 017.27) (239.86, 017.27) (239.86, 024.27) (203.99, 024.27)      /T1_1  See p. 68
-(300.32, 546.42) (440.79, 546.42) (440.79, 601.82) (300.32, 601.82)      /T1_1 2008
-(031.03, 088.97) (235.85, 094.40) (235.85, 125.05) (031.03, 145.90)      /T1_4   HOME 
-(031.03, 072.39) (305.75, 072.39) (305.75, 093.41) (031.03, 093.41)      /T1_1 IS THE MOST IMPORTANT 
+(322.16, 287.46) (386.71, 287.46) (386.71, 297.38) (322.16, 297.38)      /T1_3 KARLSTAD sofa  	<|special_separator|>
+(322.16, 265.98) (387.82, 252.69) (387.82, 292.99) (322.16, 289.48)      /T1_3 $ 599	<|special_separator|>
+(430.99, 010.48) (524.75, 010.48) (524.75, 022.88) (430.99, 022.88)      /T1_3 www.IKEA-USA.com	<|special_separator|>
+(031.03, 538.21) (347.92, 538.21) (347.92, 546.97) (031.03, 546.97)      /T1_4 ALL CATALOG PRICES ARE VALID UNTIL JUNE 30, 2008	<|special_separator|>
+(031.03, 025.16) (112.83, 025.16) (112.83, 035.08) (031.03, 035.08)      /T1_3 KARLSTAD sofa $599	<|special_separator|>
+(113.09, 025.77) (148.52, 025.77) (148.52, 032.77) (113.09, 032.77)      /T1_1  See p. 4  	<|special_separator|>
+(031.03, 016.66) (203.67, 016.66) (203.67, 026.58) (031.03, 026.58)      /T1_3 LINNARP bookcase with glass doors $349/ea	<|special_separator|>
+(203.99, 017.27) (239.86, 017.27) (239.86, 024.27) (203.99, 024.27)      /T1_1  See p. 68	<|special_separator|>
+(300.32, 546.42) (440.79, 546.42) (440.79, 601.82) (300.32, 601.82)      /T1_1 2008	<|special_separator|>
+(031.03, 088.97) (235.85, 094.40) (235.85, 125.05) (031.03, 145.90)      /T1_4   HOME 	<|special_separator|>
+(031.03, 072.39) (305.75, 072.39) (305.75, 093.41) (031.03, 093.41)      /T1_1 IS THE MOST IMPORTANT 	<|special_separator|>
 (031.03, 048.39) (264.18, 048.39) (264.18, 069.41) (031.03, 069.41)      /T1_1 PLACE IN THE WORLD

tests/data/groundtruth/cropbox_versus_mediabox_01.pdf.page_no_1.py.json.line.txt

@@ -1,39 +1,39 @@
-(322.16, 287.46) (363.87, 287.46) (363.87, 297.38) (322.16, 297.38)      /T1_3 KARLSTAD
-(366.12, 287.46) (382.62, 287.46) (382.62, 297.38) (366.12, 297.38)      /T1_3 sofa
-(322.16, 265.98) (333.34, 265.98) (333.34, 289.48) (322.16, 289.48)      /T1_3 $
-(332.85, 252.69) (387.82, 252.69) (387.82, 292.99) (332.85, 292.99)      /T1_3 599
-(430.99, 010.48) (524.75, 010.48) (524.75, 022.88) (430.99, 022.88)      /T1_3 www.IKEA-USA.com
-(031.03, 538.21) (051.42, 538.21) (051.42, 546.97) (031.03, 546.97)      /T1_4 ALL
-(055.98, 538.21) (110.11, 538.21) (110.11, 546.97) (055.98, 546.97)      /T1_4 CATALOG
-(114.72, 538.21) (154.57, 538.21) (154.57, 546.97) (114.72, 546.97)      /T1_4 PRICES
-(159.12, 538.21) (181.03, 538.21) (181.03, 546.97) (159.12, 546.97)      /T1_4 ARE
-(185.68, 538.21) (219.95, 538.21) (219.95, 546.97) (185.68, 546.97)      /T1_4 VALID
-(224.52, 538.21) (258.43, 538.21) (258.43, 546.97) (224.52, 546.97)      /T1_4 UNTIL
-(262.99, 538.21) (292.48, 538.21) (292.48, 546.97) (262.99, 546.97)      /T1_4 JUNE
-(297.03, 538.21) (314.76, 538.21) (314.76, 546.97) (297.03, 546.97)      /T1_4 30,
-(319.31, 538.21) (347.92, 538.21) (347.92, 546.97) (319.31, 546.97)      /T1_4 2008
-(031.03, 025.16) (072.17, 025.16) (072.17, 035.08) (031.03, 035.08)      /T1_3 KARLSTAD
-(074.37, 025.16) (090.87, 025.16) (090.87, 035.08) (074.37, 035.08)      /T1_3 sofa
-(093.12, 025.16) (112.83, 025.16) (112.83, 035.08) (093.12, 035.08)      /T1_3 $599
-(115.25, 025.77) (128.48, 025.77) (128.48, 032.77) (115.25, 032.77)      /T1_1 See
-(130.76, 025.77) (137.43, 025.77) (137.43, 032.77) (130.76, 032.77)      /T1_1 p.
-(139.71, 025.77) (144.20, 025.77) (144.20, 032.77) (139.71, 032.77)      /T1_1 4
-(031.03, 016.66) (065.51, 016.66) (065.51, 026.58) (031.03, 026.58)      /T1_3 LINNARP
-(067.71, 016.66) (104.30, 016.66) (104.30, 026.58) (067.71, 026.58)      /T1_3 bookcase
-(106.55, 016.66) (122.72, 016.66) (122.72, 026.58) (106.55, 026.58)      /T1_3 with
-(124.97, 016.66) (144.71, 016.66) (144.71, 026.58) (124.97, 026.58)      /T1_3 glass
-(146.96, 016.66) (168.70, 016.66) (168.70, 026.58) (146.96, 026.58)      /T1_3 doors
-(170.95, 016.66) (203.67, 016.66) (203.67, 026.58) (170.95, 026.58)      /T1_3 $349/ea
-(206.16, 017.27) (219.38, 017.27) (219.38, 024.27) (206.16, 024.27)      /T1_1 See
-(221.66, 017.27) (228.33, 017.27) (228.33, 024.27) (221.66, 024.27)      /T1_1 p.
-(230.61, 017.27) (239.86, 017.27) (239.86, 024.27) (230.61, 024.27)      /T1_1 68
-(300.32, 546.42) (440.79, 546.42) (440.79, 601.82) (300.32, 601.82)      /T1_1 2008
-(030.06, 088.97) (226.82, 088.97) (226.82, 145.90) (030.06, 145.90)      /T1_4 HOME
-(031.03, 072.39) (049.10, 072.39) (049.10, 093.41) (031.03, 093.41)      /T1_1 IS
-(055.22, 072.39) (095.92, 072.39) (095.92, 093.41) (055.22, 093.41)      /T1_1 THE
-(102.04, 072.39) (166.22, 072.39) (166.22, 093.41) (102.04, 093.41)      /T1_1 MOST
-(172.34, 072.39) (299.63, 072.39) (299.63, 093.41) (172.34, 093.41)      /T1_1 IMPORTANT
-(031.03, 048.39) (098.88, 048.39) (098.88, 069.41) (031.03, 069.41)      /T1_1 PLACE
-(105.00, 048.39) (128.13, 048.39) (128.13, 069.41) (105.00, 069.41)      /T1_1 IN
-(134.25, 048.39) (174.94, 048.39) (174.94, 069.41) (134.25, 069.41)      /T1_1 THE
+(322.16, 287.46) (363.87, 287.46) (363.87, 297.38) (322.16, 297.38)      /T1_3 KARLSTAD	<|special_separator|>
+(366.12, 287.46) (382.62, 287.46) (382.62, 297.38) (366.12, 297.38)      /T1_3 sofa	<|special_separator|>
+(322.16, 265.98) (333.34, 265.98) (333.34, 289.48) (322.16, 289.48)      /T1_3 $	<|special_separator|>
+(332.85, 252.69) (387.82, 252.69) (387.82, 292.99) (332.85, 292.99)      /T1_3 599	<|special_separator|>
+(430.99, 010.48) (524.75, 010.48) (524.75, 022.88) (430.99, 022.88)      /T1_3 www.IKEA-USA.com	<|special_separator|>
+(031.03, 538.21) (051.42, 538.21) (051.42, 546.97) (031.03, 546.97)      /T1_4 ALL	<|special_separator|>
+(055.98, 538.21) (110.11, 538.21) (110.11, 546.97) (055.98, 546.97)      /T1_4 CATALOG	<|special_separator|>
+(114.72, 538.21) (154.57, 538.21) (154.57, 546.97) (114.72, 546.97)      /T1_4 PRICES	<|special_separator|>
+(159.12, 538.21) (181.03, 538.21) (181.03, 546.97) (159.12, 546.97)      /T1_4 ARE	<|special_separator|>
+(185.68, 538.21) (219.95, 538.21) (219.95, 546.97) (185.68, 546.97)      /T1_4 VALID	<|special_separator|>
+(224.52, 538.21) (258.43, 538.21) (258.43, 546.97) (224.52, 546.97)      /T1_4 UNTIL	<|special_separator|>
+(262.99, 538.21) (292.48, 538.21) (292.48, 546.97) (262.99, 546.97)      /T1_4 JUNE	<|special_separator|>
+(297.03, 538.21) (314.76, 538.21) (314.76, 546.97) (297.03, 546.97)      /T1_4 30,	<|special_separator|>
+(319.31, 538.21) (347.92, 538.21) (347.92, 546.97) (319.31, 546.97)      /T1_4 2008	<|special_separator|>
+(031.03, 025.16) (072.17, 025.16) (072.17, 035.08) (031.03, 035.08)      /T1_3 KARLSTAD	<|special_separator|>
+(074.37, 025.16) (090.87, 025.16) (090.87, 035.08) (074.37, 035.08)      /T1_3 sofa	<|special_separator|>
+(093.12, 025.16) (112.83, 025.16) (112.83, 035.08) (093.12, 035.08)      /T1_3 $599	<|special_separator|>
+(115.25, 025.77) (128.48, 025.77) (128.48, 032.77) (115.25, 032.77)      /T1_1 See	<|special_separator|>
+(130.76, 025.77) (137.43, 025.77) (137.43, 032.77) (130.76, 032.77)      /T1_1 p.	<|special_separator|>
+(139.71, 025.77) (144.20, 025.77) (144.20, 032.77) (139.71, 032.77)      /T1_1 4	<|special_separator|>
+(031.03, 016.66) (065.51, 016.66) (065.51, 026.58) (031.03, 026.58)      /T1_3 LINNARP	<|special_separator|>
+(067.71, 016.66) (104.30, 016.66) (104.30, 026.58) (067.71, 026.58)      /T1_3 bookcase	<|special_separator|>
+(106.55, 016.66) (122.72, 016.66) (122.72, 026.58) (106.55, 026.58)      /T1_3 with	<|special_separator|>
+(124.97, 016.66) (144.71, 016.66) (144.71, 026.58) (124.97, 026.58)      /T1_3 glass	<|special_separator|>
+(146.96, 016.66) (168.70, 016.66) (168.70, 026.58) (146.96, 026.58)      /T1_3 doors	<|special_separator|>
+(170.95, 016.66) (203.67, 016.66) (203.67, 026.58) (170.95, 026.58)      /T1_3 $349/ea	<|special_separator|>
+(206.16, 017.27) (219.38, 017.27) (219.38, 024.27) (206.16, 024.27)      /T1_1 See	<|special_separator|>
+(221.66, 017.27) (228.33, 017.27) (228.33, 024.27) (221.66, 024.27)      /T1_1 p.	<|special_separator|>
+(230.61, 017.27) (239.86, 017.27) (239.86, 024.27) (230.61, 024.27)      /T1_1 68	<|special_separator|>
+(300.32, 546.42) (440.79, 546.42) (440.79, 601.82) (300.32, 601.82)      /T1_1 2008	<|special_separator|>
+(030.06, 088.97) (226.82, 088.97) (226.82, 145.90) (030.06, 145.90)      /T1_4 HOME	<|special_separator|>
+(031.03, 072.39) (049.10, 072.39) (049.10, 093.41) (031.03, 093.41)      /T1_1 IS	<|special_separator|>
+(055.22, 072.39) (095.92, 072.39) (095.92, 093.41) (055.22, 093.41)      /T1_1 THE	<|special_separator|>
+(102.04, 072.39) (166.22, 072.39) (166.22, 093.41) (102.04, 093.41)      /T1_1 MOST	<|special_separator|>
+(172.34, 072.39) (299.63, 072.39) (299.63, 093.41) (172.34, 093.41)      /T1_1 IMPORTANT	<|special_separator|>
+(031.03, 048.39) (098.88, 048.39) (098.88, 069.41) (031.03, 069.41)      /T1_1 PLACE	<|special_separator|>
+(105.00, 048.39) (128.13, 048.39) (128.13, 069.41) (105.00, 069.41)      /T1_1 IN	<|special_separator|>
+(134.25, 048.39) (174.94, 048.39) (174.94, 069.41) (134.25, 069.41)      /T1_1 THE	<|special_separator|>
 (181.06, 048.39) (264.18, 048.39) (264.18, 069.41) (181.06, 069.41)      /T1_1 WORLD