orhan/test
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: render math equations in .docx documents (#1160)

Browse Source 
* feat: math equation rendering in .docx files
* fix: import fix on .docx pre processing
* test: add test cases for docx equation rendering
* docs: add ThirdPartyNotices.md
* refactor: reformatted with black
This commit is contained in:
Sathindu
2025-03-28 18:36:38 -04:00
committed by GitHub
parent 9e067c42b6
commit 3fcd48cdfc
11 changed files with 1081 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

232
packages/markitdown/ThirdPartyNotices.md Normal file
View File

@@ -0,0 +1,232 @@
# THIRD-PARTY SOFTWARE NOTICES AND INFORMATION
**Do Not Translate or Localize**
This project incorporates components from the projects listed below. The original copyright notices and the licenses
under which MarkItDown received such components are set forth below. MarkItDown reserves all rights not expressly
granted herein, whether by implication, estoppel or otherwise.
1.dwml (https://github.com/xiilei/dwml)
dwml NOTICES AND INFORMATION BEGIN HERE
-----------------------------------------
NOTE 1: What follows is a verbatim copy of dwml's LICENSE file, as it appeared on March 28th, 2025 - including
placeholders for the copyright owner and year.
NOTE 2: The Apache License, Version 2.0, requires that modifications to the dwml source code be documented.
The following section summarizes these changes. The full details are available in the MarkItDown source code
repository under PR #1160 (https://github.com/microsoft/markitdown/pull/1160)
This project incorporates `dwml/latex_dict.py` and `dwml/omml.py` files without any additional logic modifications (which
lives in `packages/markitdown/src/markitdown/converter_utils/docx/math` location). However, we have reformatted the code
according to `black` code formatter. From `tests/docx.py` file, we have used `DOCXML_ROOT` XML namespaces and the rest of
the file is not used.
-----------------------------------------
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "{}"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright {yyyy} {name of copyright owner}
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
-----------------------------------------
END OF dwml NOTICES AND INFORMATION

3
packages/markitdown/pyproject.toml
View File

@@ -38,6 +38,7 @@ all = [
"pandas",
"openpyxl",
"xlrd",
"lxml",
"pdfminer.six",
"olefile",
"pydub",
@@ -47,7 +48,7 @@ all = [
"azure-identity"
]
pptx = ["python-pptx"]
docx = ["mammoth"]
docx = ["mammoth", "lxml"]
xlsx = ["pandas", "openpyxl"]
xls = ["pandas", "xlrd"]
pdf = ["pdfminer.six"]

0
packages/markitdown/src/markitdown/converter_utils/__init__.py Normal file
View File

0
packages/markitdown/src/markitdown/converter_utils/docx/__init__.py Normal file
View File

0
packages/markitdown/src/markitdown/converter_utils/docx/math/__init__.py Normal file
View File

273
packages/markitdown/src/markitdown/converter_utils/docx/math/latex_dict.py Normal file
View File

@@ -0,0 +1,273 @@
# -*- coding: utf-8 -*-
"""
Adapted from https://github.com/xiilei/dwml/blob/master/dwml/latex_dict.py
On 25/03/2025
"""
from __future__ import unicode_literals
CHARS = ("{", "}", "_", "^", "#", "&", "$", "%", "~")
BLANK = ""
BACKSLASH = "\\"
ALN = "&"
CHR = {
# Unicode : Latex Math Symbols
# Top accents
"\u0300": "\\grave{{{0}}}",
"\u0301": "\\acute{{{0}}}",
"\u0302": "\\hat{{{0}}}",
"\u0303": "\\tilde{{{0}}}",
"\u0304": "\\bar{{{0}}}",
"\u0305": "\\overbar{{{0}}}",
"\u0306": "\\breve{{{0}}}",
"\u0307": "\\dot{{{0}}}",
"\u0308": "\\ddot{{{0}}}",
"\u0309": "\\ovhook{{{0}}}",
"\u030a": "\\ocirc{{{0}}}}",
"\u030c": "\\check{{{0}}}}",
"\u0310": "\\candra{{{0}}}",
"\u0312": "\\oturnedcomma{{{0}}}",
"\u0315": "\\ocommatopright{{{0}}}",
"\u031a": "\\droang{{{0}}}",
"\u0338": "\\not{{{0}}}",
"\u20d0": "\\leftharpoonaccent{{{0}}}",
"\u20d1": "\\rightharpoonaccent{{{0}}}",
"\u20d2": "\\vertoverlay{{{0}}}",
"\u20d6": "\\overleftarrow{{{0}}}",
"\u20d7": "\\vec{{{0}}}",
"\u20db": "\\dddot{{{0}}}",
"\u20dc": "\\ddddot{{{0}}}",
"\u20e1": "\\overleftrightarrow{{{0}}}",
"\u20e7": "\\annuity{{{0}}}",
"\u20e9": "\\widebridgeabove{{{0}}}",
"\u20f0": "\\asteraccent{{{0}}}",
# Bottom accents
"\u0330": "\\wideutilde{{{0}}}",
"\u0331": "\\underbar{{{0}}}",
"\u20e8": "\\threeunderdot{{{0}}}",
"\u20ec": "\\underrightharpoondown{{{0}}}",
"\u20ed": "\\underleftharpoondown{{{0}}}",
"\u20ee": "\\underledtarrow{{{0}}}",
"\u20ef": "\\underrightarrow{{{0}}}",
# Over | group
"\u23b4": "\\overbracket{{{0}}}",
"\u23dc": "\\overparen{{{0}}}",
"\u23de": "\\overbrace{{{0}}}",
# Under| group
"\u23b5": "\\underbracket{{{0}}}",
"\u23dd": "\\underparen{{{0}}}",
"\u23df": "\\underbrace{{{0}}}",
}
CHR_BO = {
# Big operators,
"\u2140": "\\Bbbsum",
"\u220f": "\\prod",
"\u2210": "\\coprod",
"\u2211": "\\sum",
"\u222b": "\\int",
"\u22c0": "\\bigwedge",
"\u22c1": "\\bigvee",
"\u22c2": "\\bigcap",
"\u22c3": "\\bigcup",
"\u2a00": "\\bigodot",
"\u2a01": "\\bigoplus",
"\u2a02": "\\bigotimes",
}
T = {
"\u2192": "\\rightarrow ",
# Greek letters
"\U0001d6fc": "\\alpha ",
"\U0001d6fd": "\\beta ",
"\U0001d6fe": "\\gamma ",
"\U0001d6ff": "\\theta ",
"\U0001d700": "\\epsilon ",
"\U0001d701": "\\zeta ",
"\U0001d702": "\\eta ",
"\U0001d703": "\\theta ",
"\U0001d704": "\\iota ",
"\U0001d705": "\\kappa ",
"\U0001d706": "\\lambda ",
"\U0001d707": "\\m ",
"\U0001d708": "\\n ",
"\U0001d709": "\\xi ",
"\U0001d70a": "\\omicron ",
"\U0001d70b": "\\pi ",
"\U0001d70c": "\\rho ",
"\U0001d70d": "\\varsigma ",
"\U0001d70e": "\\sigma ",
"\U0001d70f": "\\ta ",
"\U0001d710": "\\upsilon ",
"\U0001d711": "\\phi ",
"\U0001d712": "\\chi ",
"\U0001d713": "\\psi ",
"\U0001d714": "\\omega ",
"\U0001d715": "\\partial ",
"\U0001d716": "\\varepsilon ",
"\U0001d717": "\\vartheta ",
"\U0001d718": "\\varkappa ",
"\U0001d719": "\\varphi ",
"\U0001d71a": "\\varrho ",
"\U0001d71b": "\\varpi ",
# Relation symbols
"\u2190": "\\leftarrow ",
"\u2191": "\\uparrow ",
"\u2192": "\\rightarrow ",
"\u2193": "\\downright ",
"\u2194": "\\leftrightarrow ",
"\u2195": "\\updownarrow ",
"\u2196": "\\nwarrow ",
"\u2197": "\\nearrow ",
"\u2198": "\\searrow ",
"\u2199": "\\swarrow ",
"\u22ee": "\\vdots ",
"\u22ef": "\\cdots ",
"\u22f0": "\\adots ",
"\u22f1": "\\ddots ",
"\u2260": "\\ne ",
"\u2264": "\\leq ",
"\u2265": "\\geq ",
"\u2266": "\\leqq ",
"\u2267": "\\geqq ",
"\u2268": "\\lneqq ",
"\u2269": "\\gneqq ",
"\u226a": "\\ll ",
"\u226b": "\\gg ",
"\u2208": "\\in ",
"\u2209": "\\notin ",
"\u220b": "\\ni ",
"\u220c": "\\nni ",
# Ordinary symbols
"\u221e": "\\infty ",
# Binary relations
"\u00b1": "\\pm ",
"\u2213": "\\mp ",
# Italic, Latin, uppercase
"\U0001d434": "A",
"\U0001d435": "B",
"\U0001d436": "C",
"\U0001d437": "D",
"\U0001d438": "E",
"\U0001d439": "F",
"\U0001d43a": "G",
"\U0001d43b": "H",
"\U0001d43c": "I",
"\U0001d43d": "J",
"\U0001d43e": "K",
"\U0001d43f": "L",
"\U0001d440": "M",
"\U0001d441": "N",
"\U0001d442": "O",
"\U0001d443": "P",
"\U0001d444": "Q",
"\U0001d445": "R",
"\U0001d446": "S",
"\U0001d447": "T",
"\U0001d448": "U",
"\U0001d449": "V",
"\U0001d44a": "W",
"\U0001d44b": "X",
"\U0001d44c": "Y",
"\U0001d44d": "Z",
# Italic, Latin, lowercase
"\U0001d44e": "a",
"\U0001d44f": "b",
"\U0001d450": "c",
"\U0001d451": "d",
"\U0001d452": "e",
"\U0001d453": "f",
"\U0001d454": "g",
"\U0001d456": "i",
"\U0001d457": "j",
"\U0001d458": "k",
"\U0001d459": "l",
"\U0001d45a": "m",
"\U0001d45b": "n",
"\U0001d45c": "o",
"\U0001d45d": "p",
"\U0001d45e": "q",
"\U0001d45f": "r",
"\U0001d460": "s",
"\U0001d461": "t",
"\U0001d462": "u",
"\U0001d463": "v",
"\U0001d464": "w",
"\U0001d465": "x",
"\U0001d466": "y",
"\U0001d467": "z",
}
FUNC = {
"sin": "\\sin({fe})",
"cos": "\\cos({fe})",
"tan": "\\tan({fe})",
"arcsin": "\\arcsin({fe})",
"arccos": "\\arccos({fe})",
"arctan": "\\arctan({fe})",
"arccot": "\\arccot({fe})",
"sinh": "\\sinh({fe})",
"cosh": "\\cosh({fe})",
"tanh": "\\tanh({fe})",
"coth": "\\coth({fe})",
"sec": "\\sec({fe})",
"csc": "\\csc({fe})",
}
FUNC_PLACE = "{fe}"
BRK = "\\\\"
CHR_DEFAULT = {
"ACC_VAL": "\\hat{{{0}}}",
}
POS = {
"top": "\\overline{{{0}}}", # not sure
"bot": "\\underline{{{0}}}",
}
POS_DEFAULT = {
"BAR_VAL": "\\overline{{{0}}}",
}
SUB = "_{{{0}}}"
SUP = "^{{{0}}}"
F = {
"bar": "\\frac{{{num}}}{{{den}}}",
"skw": r"^{{{num}}}/_{{{den}}}",
"noBar": "\\genfrac{{}}{{}}{{0pt}}{{}}{{{num}}}{{{den}}}",
"lin": "{{{num}}}/{{{den}}}",
}
F_DEFAULT = "\\frac{{{num}}}{{{den}}}"
D = "\\left{left}{text}\\right{right}"
D_DEFAULT = {
"left": "(",
"right": ")",
"null": ".",
}
RAD = "\\sqrt[{deg}]{{{text}}}"
RAD_DEFAULT = "\\sqrt{{{text}}}"
ARR = "\\begin{{array}}{{c}}{text}\\end{{array}}"
LIM_FUNC = {
"lim": "\\lim_{{{lim}}}",
"max": "\\max_{{{lim}}}",
"min": "\\min_{{{lim}}}",
}
LIM_TO = ("\\rightarrow", "\\to")
LIM_UPP = "\\overset{{{lim}}}{{{text}}}"
M = "\\begin{{matrix}}{text}\\end{{matrix}}"

400
packages/markitdown/src/markitdown/converter_utils/docx/math/omml.py Normal file
View File

@@ -0,0 +1,400 @@
# -*- coding: utf-8 -*-
"""
Office Math Markup Language (OMML)
Adapted from https://github.com/xiilei/dwml/blob/master/dwml/omml.py
On 25/03/2025
"""
import xml.etree.ElementTree as ET
from .latex_dict import (
CHARS,
CHR,
CHR_BO,
CHR_DEFAULT,
POS,
POS_DEFAULT,
SUB,
SUP,
F,
F_DEFAULT,
T,
FUNC,
D,
D_DEFAULT,
RAD,
RAD_DEFAULT,
ARR,
LIM_FUNC,
LIM_TO,
LIM_UPP,
M,
BRK,
BLANK,
BACKSLASH,
ALN,
FUNC_PLACE,
)
OMML_NS = "{http://schemas.openxmlformats.org/officeDocument/2006/math}"
def load(stream):
tree = ET.parse(stream)
for omath in tree.findall(OMML_NS + "oMath"):
yield oMath2Latex(omath)
def load_string(string):
root = ET.fromstring(string)
for omath in root.findall(OMML_NS + "oMath"):
yield oMath2Latex(omath)
def escape_latex(strs):
last = None
new_chr = []
strs = strs.replace(r"\\", "\\")
for c in strs:
if (c in CHARS) and (last != BACKSLASH):
new_chr.append(BACKSLASH + c)
else:
new_chr.append(c)
last = c
return BLANK.join(new_chr)
def get_val(key, default=None, store=CHR):
if key is not None:
return key if not store else store.get(key, key)
else:
return default
class Tag2Method(object):
def call_method(self, elm, stag=None):
getmethod = self.tag2meth.get
if stag is None:
stag = elm.tag.replace(OMML_NS, "")
method = getmethod(stag)
if method:
return method(self, elm)
else:
return None
def process_children_list(self, elm, include=None):
"""
process children of the elm,return iterable
"""
for _e in list(elm):
if OMML_NS not in _e.tag:
continue
stag = _e.tag.replace(OMML_NS, "")
if include and (stag not in include):
continue
t = self.call_method(_e, stag=stag)
if t is None:
t = self.process_unknow(_e, stag)
if t is None:
continue
yield (stag, t, _e)
def process_children_dict(self, elm, include=None):
"""
process children of the elm,return dict
"""
latex_chars = dict()
for stag, t, e in self.process_children_list(elm, include):
latex_chars[stag] = t
return latex_chars
def process_children(self, elm, include=None):
"""
process children of the elm,return string
"""
return BLANK.join(
(
t if not isinstance(t, Tag2Method) else str(t)
for stag, t, e in self.process_children_list(elm, include)
)
)
def process_unknow(self, elm, stag):
return None
class Pr(Tag2Method):
text = ""
__val_tags = ("chr", "pos", "begChr", "endChr", "type")
__innerdict = None # can't use the __dict__
""" common properties of element"""
def __init__(self, elm):
self.__innerdict = {}
self.text = self.process_children(elm)
def __str__(self):
return self.text
def __unicode__(self):
return self.__str__(self)
def __getattr__(self, name):
return self.__innerdict.get(name, None)
def do_brk(self, elm):
self.__innerdict["brk"] = BRK
return BRK
def do_common(self, elm):
stag = elm.tag.replace(OMML_NS, "")
if stag in self.__val_tags:
t = elm.get("{0}val".format(OMML_NS))
self.__innerdict[stag] = t
return None
tag2meth = {
"brk": do_brk,
"chr": do_common,
"pos": do_common,
"begChr": do_common,
"endChr": do_common,
"type": do_common,
}
class oMath2Latex(Tag2Method):
"""
Convert oMath element of omml to latex
"""
_t_dict = T
__direct_tags = ("box", "sSub", "sSup", "sSubSup", "num", "den", "deg", "e")
def __init__(self, element):
self._latex = self.process_children(element)
def __str__(self):
return self.latex
def __unicode__(self):
return self.__str__(self)
def process_unknow(self, elm, stag):
if stag in self.__direct_tags:
return self.process_children(elm)
elif stag[-2:] == "Pr":
return Pr(elm)
else:
return None
@property
def latex(self):
return self._latex
def do_acc(self, elm):
"""
the accent function
"""
c_dict = self.process_children_dict(elm)
latex_s = get_val(
c_dict["accPr"].chr, default=CHR_DEFAULT.get("ACC_VAL"), store=CHR
)
return latex_s.format(c_dict["e"])
def do_bar(self, elm):
"""
the bar function
"""
c_dict = self.process_children_dict(elm)
pr = c_dict["barPr"]
latex_s = get_val(pr.pos, default=POS_DEFAULT.get("BAR_VAL"), store=POS)
return pr.text + latex_s.format(c_dict["e"])
def do_d(self, elm):
"""
the delimiter object
"""
c_dict = self.process_children_dict(elm)
pr = c_dict["dPr"]
null = D_DEFAULT.get("null")
s_val = get_val(pr.begChr, default=D_DEFAULT.get("left"), store=T)
e_val = get_val(pr.endChr, default=D_DEFAULT.get("right"), store=T)
return pr.text + D.format(
left=null if not s_val else escape_latex(s_val),
text=c_dict["e"],
right=null if not e_val else escape_latex(e_val),
)
def do_spre(self, elm):
"""
the Pre-Sub-Superscript object -- Not support yet
"""
pass
def do_sub(self, elm):
text = self.process_children(elm)
return SUB.format(text)
def do_sup(self, elm):
text = self.process_children(elm)
return SUP.format(text)
def do_f(self, elm):
"""
the fraction object
"""
c_dict = self.process_children_dict(elm)
pr = c_dict["fPr"]
latex_s = get_val(pr.type, default=F_DEFAULT, store=F)
return pr.text + latex_s.format(num=c_dict.get("num"), den=c_dict.get("den"))
def do_func(self, elm):
"""
the Function-Apply object (Examples:sin cos)
"""
c_dict = self.process_children_dict(elm)
func_name = c_dict.get("fName")
return func_name.replace(FUNC_PLACE, c_dict.get("e"))
def do_fname(self, elm):
"""
the func name
"""
latex_chars = []
for stag, t, e in self.process_children_list(elm):
if stag == "r":
if FUNC.get(t):
latex_chars.append(FUNC[t])
else:
raise NotImplemented("Not support func %s" % t)
else:
latex_chars.append(t)
t = BLANK.join(latex_chars)
return t if FUNC_PLACE in t else t + FUNC_PLACE # do_func will replace this
def do_groupchr(self, elm):
"""
the Group-Character object
"""
c_dict = self.process_children_dict(elm)
pr = c_dict["groupChrPr"]
latex_s = get_val(pr.chr)
return pr.text + latex_s.format(c_dict["e"])
def do_rad(self, elm):
"""
the radical object
"""
c_dict = self.process_children_dict(elm)
text = c_dict.get("e")
deg_text = c_dict.get("deg")
if deg_text:
return RAD.format(deg=deg_text, text=text)
else:
return RAD_DEFAULT.format(text=text)
def do_eqarr(self, elm):
"""
the Array object
"""
return ARR.format(
text=BRK.join(
[t for stag, t, e in self.process_children_list(elm, include=("e",))]
)
)
def do_limlow(self, elm):
"""
the Lower-Limit object
"""
t_dict = self.process_children_dict(elm, include=("e", "lim"))
latex_s = LIM_FUNC.get(t_dict["e"])
if not latex_s:
raise NotImplemented("Not support lim %s" % t_dict["e"])
else:
return latex_s.format(lim=t_dict.get("lim"))
def do_limupp(self, elm):
"""
the Upper-Limit object
"""
t_dict = self.process_children_dict(elm, include=("e", "lim"))
return LIM_UPP.format(lim=t_dict.get("lim"), text=t_dict.get("e"))
def do_lim(self, elm):
"""
the lower limit of the limLow object and the upper limit of the limUpp function
"""
return self.process_children(elm).replace(LIM_TO[0], LIM_TO[1])
def do_m(self, elm):
"""
the Matrix object
"""
rows = []
for stag, t, e in self.process_children_list(elm):
if stag == "mPr":
pass
elif stag == "mr":
rows.append(t)
return M.format(text=BRK.join(rows))
def do_mr(self, elm):
"""
a single row of the matrix m
"""
return ALN.join(
[t for stag, t, e in self.process_children_list(elm, include=("e",))]
)
def do_nary(self, elm):
"""
the n-ary object
"""
res = []
bo = ""
for stag, t, e in self.process_children_list(elm):
if stag == "naryPr":
bo = get_val(t.chr, store=CHR_BO)
else:
res.append(t)
return bo + BLANK.join(res)
def do_r(self, elm):
"""
Get text from 'r' element,And try convert them to latex symbols
@todo text style support , (sty)
@todo \text (latex pure text support)
"""
_str = []
for s in elm.findtext("./{0}t".format(OMML_NS)):
# s = s if isinstance(s,unicode) else unicode(s,'utf-8')
_str.append(self._t_dict.get(s, s))
return escape_latex(BLANK.join(_str))
tag2meth = {
"acc": do_acc,
"r": do_r,
"bar": do_bar,
"sub": do_sub,
"sup": do_sup,
"f": do_f,
"func": do_func,
"fName": do_fname,
"groupChr": do_groupchr,
"d": do_d,
"rad": do_rad,
"eqArr": do_eqarr,
"limLow": do_limlow,
"limUpp": do_limupp,
"lim": do_lim,
"m": do_m,
"mr": do_mr,
"nary": do_nary,
}

156
packages/markitdown/src/markitdown/converter_utils/docx/pre_process.py Normal file
View File

@@ -0,0 +1,156 @@
import zipfile
from io import BytesIO
from typing import BinaryIO
from xml.etree import ElementTree as ET
from bs4 import BeautifulSoup, Tag
from .math.omml import OMML_NS, oMath2Latex
MATH_ROOT_TEMPLATE = "".join(
(
"<w:document ",
'xmlns:wpc="http://schemas.microsoft.com/office/word/2010/wordprocessingCanvas" ',
'xmlns:mc="http://schemas.openxmlformats.org/markup-compatibility/2006" ',
'xmlns:o="urn:schemas-microsoft-com:office:office" ',
'xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships" ',
'xmlns:m="http://schemas.openxmlformats.org/officeDocument/2006/math" ',
'xmlns:v="urn:schemas-microsoft-com:vml" ',
'xmlns:wp14="http://schemas.microsoft.com/office/word/2010/wordprocessingDrawing" ',
'xmlns:wp="http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing" ',
'xmlns:w10="urn:schemas-microsoft-com:office:word" ',
'xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main" ',
'xmlns:w14="http://schemas.microsoft.com/office/word/2010/wordml" ',
'xmlns:wpg="http://schemas.microsoft.com/office/word/2010/wordprocessingGroup" ',
'xmlns:wpi="http://schemas.microsoft.com/office/word/2010/wordprocessingInk" ',
'xmlns:wne="http://schemas.microsoft.com/office/word/2006/wordml" ',
'xmlns:wps="http://schemas.microsoft.com/office/word/2010/wordprocessingShape" mc:Ignorable="w14 wp14">',
"{0}</w:document>",
)
)
def _convert_omath_to_latex(tag: Tag) -> str:
"""
Converts an OMML (Office Math Markup Language) tag to LaTeX format.
Args:
tag (Tag): A BeautifulSoup Tag object representing the OMML element.
Returns:
str: The LaTeX representation of the OMML element.
"""
# Format the tag into a complete XML document string
math_root = ET.fromstring(MATH_ROOT_TEMPLATE.format(str(tag)))
# Find the 'oMath' element within the XML document
math_element = math_root.find(OMML_NS + "oMath")
# Convert the 'oMath' element to LaTeX using the oMath2Latex function
latex = oMath2Latex(math_element).latex
return latex
def _get_omath_tag_replacement(tag: Tag, block: bool = False) -> Tag:
"""
Creates a replacement tag for an OMML (Office Math Markup Language) element.
Args:
tag (Tag): A BeautifulSoup Tag object representing the "oMath" element.
block (bool, optional): If True, the LaTeX will be wrapped in double dollar signs for block mode. Defaults to False.
Returns:
Tag: A BeautifulSoup Tag object representing the replacement element.
"""
t_tag = Tag(name="w:t")
t_tag.string = (
f"$${_convert_omath_to_latex(tag)}$$"
if block
else f"${_convert_omath_to_latex(tag)}$"
)
r_tag = Tag(name="w:r")
r_tag.append(t_tag)
return r_tag
def _replace_equations(tag: Tag):
"""
Replaces OMML (Office Math Markup Language) elements with their LaTeX equivalents.
Args:
tag (Tag): A BeautifulSoup Tag object representing the OMML element. Could be either "oMathPara" or "oMath".
Raises:
ValueError: If the tag is not supported.
"""
if tag.name == "oMathPara":
# Create a new paragraph tag
p_tag = Tag(name="w:p")
# Replace each 'oMath' child tag with its LaTeX equivalent as block equations
for child_tag in tag.find_all("oMath"):
p_tag.append(_get_omath_tag_replacement(child_tag, block=True))
# Replace the original 'oMathPara' tag with the new paragraph tag
tag.replace_with(p_tag)
elif tag.name == "oMath":
# Replace the 'oMath' tag with its LaTeX equivalent as inline equation
tag.replace_with(_get_omath_tag_replacement(tag, block=False))
else:
raise ValueError(f"Not supported tag: {tag.name}")
def _pre_process_math(content: bytes) -> bytes:
"""
Pre-processes the math content in a DOCX -> XML file by converting OMML (Office Math Markup Language) elements to LaTeX.
This preprocessed content can be directly replaced in the DOCX file -> XMLs.
Args:
content (bytes): The XML content of the DOCX file as bytes.
Returns:
bytes: The processed content with OMML elements replaced by their LaTeX equivalents, encoded as bytes.
"""
soup = BeautifulSoup(content.decode(), features="xml")
for tag in soup.find_all("oMathPara"):
_replace_equations(tag)
for tag in soup.find_all("oMath"):
_replace_equations(tag)
return str(soup).encode()
def pre_process_docx(input_docx: BinaryIO) -> BinaryIO:
"""
Pre-processes a DOCX file with provided steps.
The process works by unzipping the DOCX file in memory, transforming specific XML files
(such as converting OMML elements to LaTeX), and then zipping everything back into a
DOCX file without writing to disk.
Args:
input_docx (BinaryIO): A binary input stream representing the DOCX file.
Returns:
BinaryIO: A binary output stream representing the processed DOCX file.
"""
output_docx = BytesIO()
# The files that need to be pre-processed from .docx
pre_process_enable_files = [
"word/document.xml",
"word/footnotes.xml",
"word/endnotes.xml",
]
with zipfile.ZipFile(input_docx, mode="r") as zip_input:
files = {name: zip_input.read(name) for name in zip_input.namelist()}
with zipfile.ZipFile(output_docx, mode="w") as zip_output:
zip_output.comment = zip_input.comment
for name, content in files.items():
if name in pre_process_enable_files:
try:
# Pre-process the content
updated_content = _pre_process_math(content)
# In the future, if there are more pre-processing steps, they can be added here
zip_output.writestr(name, updated_content)
except:
# If there is an error in processing the content, write the original content
zip_output.writestr(name, content)
else:
zip_output.writestr(name, content)
output_docx.seek(0)
return output_docx

5
packages/markitdown/src/markitdown/converters/_docx_converter.py
View File

@@ -3,6 +3,7 @@ import sys
from typing import BinaryIO, Any
from ._html_converter import HtmlConverter
from ..converter_utils.docx.pre_process import pre_process_docx
from .._base_converter import DocumentConverter, DocumentConverterResult
from .._stream_info import StreamInfo
from .._exceptions import MissingDependencyException, MISSING_DEPENDENCY_MESSAGE
@@ -72,6 +73,8 @@ class DocxConverter(HtmlConverter):
)
style_map = kwargs.get("style_map", None)
pre_process_stream = pre_process_docx(file_stream)
return self._html_converter.convert_string(
mammoth.convert_to_html(file_stream, style_map=style_map).value, **kwargs
mammoth.convert_to_html(pre_process_stream, style_map=style_map).value,
**kwargs,
)

BIN
packages/markitdown/tests/test_files/equations.docx vendored Normal file
View File

Binary file not shown.

14
packages/markitdown/tests/test_module_misc.py
View File

@@ -1,6 +1,7 @@
#!/usr/bin/env python3 -m pytest
import io
import os
import re
import shutil
import openai
import pytest
@@ -262,6 +263,19 @@ def test_docx_comments() -> None:
validate_strings(result, DOCX_COMMENT_TEST_STRINGS)
def test_docx_equations() -> None:
markitdown = MarkItDown()
docx_file = os.path.join(TEST_FILES_DIR, "equations.docx")
result = markitdown.convert(docx_file)
# Check for inline equation m=1 (wrapped with single $) is present
assert "$m=1$" in result.text_content, "Inline equation $m=1$ not found"
# Find block equations wrapped with double $$ and check if they are present
block_equations = re.findall(r"\$\$(.+?)\$\$", result.text_content)
assert block_equations, "No block equations found in the document."
def test_input_as_strings() -> None:
markitdown = MarkItDown()