From 7356d165baf01c6e3876be8436aaba180b00c487 Mon Sep 17 00:00:00 2001
From: HuangHai <10402852@qq.com>
Date: Mon, 30 Jun 2025 19:50:38 +0800
Subject: [PATCH] 'commit'

---
 dsRag/Test/TestPandoc.py                      |   6 ++----
 dsRag/Util/DocxUtil.py                        |  15 +++++++--------
 .../Util/__pycache__/DocxUtil.cpython-310.pyc | Bin 1398 -> 1407 bytes
 3 files changed, 9 insertions(+), 12 deletions(-)

diff --git a/dsRag/Test/TestPandoc.py b/dsRag/Test/TestPandoc.py
index ad71fa35..65cd0d1a 100644
--- a/dsRag/Test/TestPandoc.py
+++ b/dsRag/Test/TestPandoc.py
@@ -5,8 +5,6 @@ if __name__ == '__main__':
     docx_file = 'D:\dsWork\dsProject\dsRag\static\Txt\化学方程式_CHEMISTRY_1.docx'
 
     # 整合最终的拼接完的文本
-    sb = get_docx_content_by_pandoc(docx_file)
+    content = get_docx_content_by_pandoc(docx_file)
 
-    # 输出
-    for x in sb:
-        print(x)
+    print(content)
\ No newline at end of file
diff --git a/dsRag/Util/DocxUtil.py b/dsRag/Util/DocxUtil.py
index 83946eff..fdad080e 100644
--- a/dsRag/Util/DocxUtil.py
+++ b/dsRag/Util/DocxUtil.py
@@ -3,6 +3,7 @@ import subprocess
 import os
 import uuid
 
+
 # 获取MathType对应的Latex公式
 def get_latex_list(docx_file):
     # 获取当前目录的父级目录
@@ -18,13 +19,13 @@ def get_latex_list(docx_file):
             res.append(line.strip())
     return res
 
+
 # 结合Pandoc和mtef-go的结果，合并成最终的输出文本
 def get_docx_content_by_pandoc(docx_file):
     # 一、获取Latex公式列表
     formula_list = get_latex_list(docx_file)
-
-    # StringBuilder结果
-    sb = []
+    # 最后拼接的内容
+    content = ""
     # output_file 设置为临时目录下的uuid.md
     temp_markdown = os.path.join(os.environ['TEMP'], uuid.uuid4().hex + '.md')
     # 调用pandoc将docx文件转换成markdown
@@ -37,13 +38,11 @@ def get_docx_content_by_pandoc(docx_file):
                 # 改进后的正则表达式，匹配更多格式的MathType公式
                 if re.search(r'!\[]\(media/image\d+\.\w+\)', line) or \
                         re.search(r'\.!\[]\(media/image\d+\.\w+\)\.', line):
-                    sb.append(formula_list[idx])
+                    content = content + formula_list[idx] + "\n"
                     idx = idx + 1
                 else:
-                    sb.append(line.strip())
+                    content = content + line.strip() + "\n"
 
     # 删除临时文件 output_file
     os.remove(temp_markdown)
-    return sb
-
-
+    return content
diff --git a/dsRag/Util/__pycache__/DocxUtil.cpython-310.pyc b/dsRag/Util/__pycache__/DocxUtil.cpython-310.pyc
index fe0e16eede2dbb1c2107097bfc9e2a2989d312e3..ae1b8836979fca5aefabfcdc6991d5008747617b 100644
GIT binary patch
delta 381
zcmXw!u}T9$5Qb-G_j2dvE;(&tL}DQ-NfA)NIz=p1L_{nEi6csi3%M+au!oU!f~2??
zxT`J1w~>@~zJS=pxq$n#-|WuM%<TT?xef+Fpn=!dWA8rt2%b@R=@bv2J~?N=!bBv3
zM1n^2F_TP1SO?=|r5yS$$r|LCNaJNoq%4p_C34B5B`fc|TnHeYD5I^UGWis|%IRLh
zUAu6#lQ`DN$~na6#?Jz(SSQC(XK}9D9$(@ki&j`whZ;~=g9NRjWsYjtW@l0S?+n`)
zK%iI?DIoH8VRZe#;|pE#HX^H7Sv<(%88lapXOO<jv7QP2E%>X=YI>kf(ihe6+?zpU
zZX=VvsqX12d!ucJhYB0G#tenW@=*(%hs+RhjKAx1?JE(tie9C7i$lCwz%5WIuu-6u
KcAR~w{O}JU<xjx?

delta 373
zcmW-cK}rKL6oy}3lFoEGGwnhw6{(0QbyE}%po_W?M3F9}pf1XTN*79J21LkUrEBeC
zE|58bpf~XnUO?Q{m&s4QynK)!vI>5K=rM`{;5B+4-w!^bR}@~c#M75=b{QC0h+Iq{
z$4pGoN~R*wflS+42~&@-4JGC>^KG4^0aB!?MjrV_PW(~`pn9&dz(@+HLE)QR9^~9Q
zfZN?%8*LjUB*QGU5k*Fqn4VN~Y;O3HoEx;U5k_^uRT)LiHsos7uYC2``C0!O2oz@_
z1w8nNklsD9cNy`{gl!sGHQ*5TTNlNboO?flf4JW&j@6}3)_5-7Raas<E<V-ZYMn*8
z$M8|fE^eU0mhd?t1_D<xGe(@_-{vX^l}LK7td{KXk!(A74za_QL$5f~M^c8(e?44F
A`v3p{