From 7fc19bd56e690c6d8d0c5b779eb18f0c0da09af5 Mon Sep 17 00:00:00 2001
From: HuangHai <10402852@qq.com>
Date: Mon, 30 Jun 2025 20:14:00 +0800
Subject: [PATCH] 'commit'

---
 dsRag/Util/DocxUtil.py                        |  40 ++++++++++--------
 .../Util/__pycache__/DocxUtil.cpython-310.pyc | Bin 1519 -> 1631 bytes
 2 files changed, 23 insertions(+), 17 deletions(-)

diff --git a/dsRag/Util/DocxUtil.py b/dsRag/Util/DocxUtil.py
index d4b7b7c7..bb9fcfb5 100644
--- a/dsRag/Util/DocxUtil.py
+++ b/dsRag/Util/DocxUtil.py
@@ -38,23 +38,29 @@ def get_docx_content_by_pandoc(docx_file):
     img_idx = 0  # 图片索引
     with open(temp_markdown, 'r', encoding='utf-8') as f:
         for line in f:
-            if line.strip():
-                # 改进后的正则表达式，匹配更多格式的MathType公式
-                """
-                ![](media/image1.wmf)
-                问题2 氢气与氧气燃烧的方程式
-                .![](media/image2.wmf).
-                问题3 我是一个图片
-                ![](media/image3.png){width="3.1251607611548557in" height="3.694634733158355in"}
-                """
-                if line.index("![](media/image") >= 0 and line.index(".wmf") > 0:
-                    content = content + formula_list[wmf_idx] + "\n"
-                    wmf_idx = wmf_idx + 1
-                elif line.index("![](media/image") >= 0 and (
-                        line.index(".png") > 0 or line.index(".jpg") > 0 or line.index(".jpeg") > 0):
-                    content = content + "【图片" + str(img_idx) + "】\n"
-                else:
-                    content = content + line.strip() + "\n"
+            line = line.strip()
+            if not line:
+                continue
+            # 跳过图片高度描述行
+            if line.startswith('height=') and line.endswith('in"}'):
+                continue
+            # 使用find()方法安全地检查图片模式
+            is_wmf = line.find("![](media/image") >= 0 and line.find(".wmf") > 0
+            is_img = line.find("![](media/image") >= 0 and (
+                    line.find(".png") > 0 or
+                    line.find(".jpg") > 0 or
+                    line.find(".jpeg") > 0
+            )
+            if is_wmf:
+                content += formula_list[wmf_idx] + "\n"
+                wmf_idx += 1
+            elif is_img:
+                #![](media/image3.png){width="3.1251607611548557in"
+                # height="3.694634733158355in"}
+                img_idx += 1
+                content += "【图片" + str(img_idx) + "】\n"
+            else:
+                content += line.strip() + "\n"
 
     # 删除临时文件 output_file
     os.remove(temp_markdown)
diff --git a/dsRag/Util/__pycache__/DocxUtil.cpython-310.pyc b/dsRag/Util/__pycache__/DocxUtil.cpython-310.pyc
index bcca2d20732f632e8ac312e51b43efd48f1979f7..b8e44d4234614e2f2913e2eacb4b2f5cdba10525 100644
GIT binary patch
delta 511
zcmY+Azfapx5XawL?j^>=#!w(o5Ca>CR$=Lnp<PJ3BE*0|R0#AO$DlZgZ4otkR#dTf
zc^eb{6FRp4N0%&}nL2c?;OvNjce)>+``-JZ_jmSB-RU`wEqHw$UvysmaDJg%VBvf0
z$%*-mr{h6Z)zy~x(#~qSb~l@gA}8+$O{ThXbBJ49Iclz`%C4)t9F%<}dk3tzYQ7}O
ztdgFzZb=JMtv{s~&uFor@fBq=+KMxc8Z@m6wbT%AMTVNxGH2o|XX5W#mLxT*MmneE
z4K##WnNIQq@@4$=r@e#bkx+uzZYm%mYgZ)s5I_`m%$~xXrz<&kw8TTPwQ6ko?AAJd
z7<AGPBMPI<%<NNRZA7p8QNZ!CAB-eNKbU}h5Bz=R8?C^+xuw>&ouub+nhe9VGqL<g
zO)F}Lk(yMJG@evrzuUX^w`}u|K6xkAFgY7`+hq>Bfq5sJt&e=9g@haU5=jzxV6hP(
qEF!`>y5K?`@S%?QpQHyiYgT0$77*{(AM7=Pc*oqz4cIY1<(o$Ypna48

delta 417
zcmcc5^PZbGpO=@50SG?VCS`DK<lV)@#{uMlgq(r6*kJNirkMJeTDBTC7lzotTJ{?D
z1>6f6iW)f?fGnOAzJ-h_T-mHeL0}#~n8yO-G1V~Eut+k9Go%QJGt@HGu%rkAX_i6*
z6kU~Io)AP=aUPf_jKUKE@zk?fiYjZEQbffWN_cBnn;C(|ih+y;8pj0G1auJCqREUb
zVzNEujEoE*7zxBBj0^Z`m=^*?YM6o<G{q;Iu()~gD@Mm^<ff)%ChBMACZ?xWvFMfO
zrrl!XddUd%GLTo0mkuPe3eu}sfn;iWDJM|;al?eCv-dskY%gU2^Cog>@=w0Z;v&kL
znU|7Uaf`XQr05n~QEF~}S*j+-WJgxl$<tU3jC6pCIha_O<d~$GSXfyY1sFMikcml#
nU4W5`k&jV}QH)W5iK&6<z07|uQ5MD`t;t+$a*SG&HQCGn?wV!B