From 87e02601c8d56029ed57257184b4be30f0d7e3a9 Mon Sep 17 00:00:00 2001
From: HuangHai <10402852@qq.com>
Date: Mon, 30 Jun 2025 07:53:08 +0800
Subject: [PATCH] 'commit'

---
 dsRag/ElasticSearch/T2_SplitTxt.py            |   9 +--
 dsRag/Util/WordImageUtil.py                   |  72 ------------------
 .../__pycache__/WordImageUtil.cpython-310.pyc | Bin 1766 -> 0 bytes
 3 files changed, 3 insertions(+), 78 deletions(-)
 delete mode 100644 dsRag/Util/WordImageUtil.py
 delete mode 100644 dsRag/Util/__pycache__/WordImageUtil.cpython-310.pyc

diff --git a/dsRag/ElasticSearch/T2_SplitTxt.py b/dsRag/ElasticSearch/T2_SplitTxt.py
index 2d1c224f..2ecc8660 100644
--- a/dsRag/ElasticSearch/T2_SplitTxt.py
+++ b/dsRag/ElasticSearch/T2_SplitTxt.py
@@ -1,13 +1,10 @@
-import re
-import warnings
-
-import docx
-
 import os
+import re
 import shutil
-import uuid
+import warnings
 import zipfile
 
+import docx
 from docx import Document
 from docx.oxml.ns import nsmap
 
diff --git a/dsRag/Util/WordImageUtil.py b/dsRag/Util/WordImageUtil.py
deleted file mode 100644
index a887f482..00000000
--- a/dsRag/Util/WordImageUtil.py
+++ /dev/null
@@ -1,72 +0,0 @@
-import os
-import shutil
-import uuid
-import zipfile
-
-from docx import Document
-from docx.oxml.ns import nsmap
-
-
-def extract_images_from_docx(docx_path, output_folder):
-    """
-    从docx提取图片并记录位置
-    :param docx_path: Word文档路径
-    :param output_folder: 图片输出文件夹
-    :return: 包含图片路径和位置的列表
-    """
-    # 创建一个List<String> 记录每个图片的名称和序号
-    image_data = []
-    # 创建临时解压目录
-    temp_dir = os.path.join(output_folder, "temp_docx")
-    os.makedirs(temp_dir, exist_ok=True)
-
-    # 解压docx文件
-    with zipfile.ZipFile(docx_path, 'r') as zip_ref:
-        zip_ref.extractall(temp_dir)
-
-    # 读取主文档关系
-    with open(os.path.join(temp_dir, 'word', '_rels', 'document.xml.rels'), 'r') as rels_file:
-        rels_content = rels_file.read()
-
-    # 加载主文档
-    doc = Document(docx_path)
-    img_counter = 1
-
-    # 遍历所有段落
-    for para_idx, paragraph in enumerate(doc.paragraphs):
-        for run_idx, run in enumerate(paragraph.runs):
-            # 检查运行中的图形
-            for element in run._element:
-                if element.tag.endswith('drawing'):
-                    # 提取图片关系ID
-                    blip = element.find('.//a:blip', namespaces=nsmap)
-                    if blip is not None:
-                        embed_id = blip.get('{%s}embed' % nsmap['r'])
-
-                        # 从关系文件中获取图片文件名
-                        rel_entry = f'<Relationship Id="{embed_id}"'
-                        if rel_entry in rels_content:
-                            start = rels_content.find(rel_entry)
-                            target_start = rels_content.find('Target="', start) + 8
-                            target_end = rels_content.find('"', target_start)
-                            image_path = rels_content[target_start:target_end]
-
-                            # 构建图片源路径
-                            src_path = os.path.join(temp_dir, 'word', image_path.replace('..', '').lstrip('/'))
-
-                            if os.path.exists(src_path):
-                                # 创建输出文件名
-                                ext = os.path.splitext(src_path)[1]
-                                # 名称为uuid
-                                fileName=uuid.uuid4().hex
-                                img_name = f"{fileName}{ext}"
-                                image_data.append(img_name)
-                                dest_path = os.path.join(output_folder, img_name)
-                                # 复制图片
-                                shutil.copy(src_path, dest_path)
-
-                                img_counter += 1
-
-    # 清理临时目录
-    shutil.rmtree(temp_dir)
-    return image_data
diff --git a/dsRag/Util/__pycache__/WordImageUtil.cpython-310.pyc b/dsRag/Util/__pycache__/WordImageUtil.cpython-310.pyc
deleted file mode 100644
index c91992519f8544fdc99cae9e46c21d500ad5ec8d..0000000000000000000000000000000000000000
GIT binary patch
literal 0
HcmV?d00001

literal 1766
zcmZWq|7#pY6rY*hyW89BU6RZ9SW5^h=9ddXRS2yJ#zH|#sny~VS++Nu%U<_eXXi|M
z&VrDZDzv63RxlK9(H|6{`iqrX(m!N=ZLdxLh5n$v*-LASGwhr9-n@D9-sinx<66x`
zFlwiqjrT_oy03)i2La(-_|jD%6j2-?d$?j77c#L)v1+ykD+%<lWS6kA(SmYVu`9sq
zv~&sC2E`wurSfC&gibDDX{^SrZs<iE_)?UHZqicMJstDFKuG94_)>`xYNL#B)WLls
zFvU5^G>|l*Q9`wA1S78ZO9C#-$xbcPh2Ad<Eyoz0MYN<N9c^nEMaCN_eQgu8YJLJA
zuN?T)Xqi^1k?U07COcME5~aS8qpbYD^T%H}UlnK@XBAq_3~q`_XJi|%qEC0$NLI~E
z(3l;o&|C)1NM;GEQ-l31tBG2t-XEoAj@f<S$LI(jr`9!+)kU3_x=LH`H)svC`W%`@
zInG9DU5xG`I(k#f#>AK?e}=%S+y@?Z#}!A%#CT5V_zcP#g*+-6fYpR3i-wrEOy*EF
z`CrCjvOhr^bRsAHNjjP1T+614-6=7p;wt!Q#nURBoaQtA*&KD|vKcY6i^TLUx=FHG
zLHhGzR$+bM8G}T!IsQ`rkeCv4IaEg&wE8y6j0@`*oC_br&dbB<2m(zp)%^piY%aif
zaQAB(x3(VcTp#S*80_AA^wpKYo!k4jejn_8_h9eZqrF>&*-GLvH(XGrPU7;7m4&l0
zqYrOfd6@sW|L1RmdzYR!i@QAOa%VjbsK-_ohHm%oeLJ}F7aVzT_x9kYJ41Ws@h*$N
z<m%<Y^<NJR3x9)et`6^i^uwjWm*4N_KNlzLD)+*~QGuLMP3>*@DR<)Y60?(1--MuK
z$zfiQ_Qt`c==bJU7&MjYF?2PO70TRAKWg`?&E;ix<y_z=;K+>J&`T4y<)yvq=dY%j
z7oPKIuW|IW7r5MyqjbYh7EaJ(i%;-k&p6|<w#SbxJ~qH*k2ISSJ;BRMhb4(qsVjt}
z-iiH48lijMqdrSzrROK>e&ET9?I*_-V|rVhxh?Jnfz;!~i=@sxmooJ%Wz~xydggMl
zQ{cCmn{0q@){RnWI9}kXw=6a8wgH8RrklRHbls0A)06`Z0+bczB>^NQ%R$PSpU83n
z7<fpNz~>Nv)Vp0DKvVRH)Hb{=S#}c$hRSlf(d9nG){2vhvdluxJa1`UR-d(jU3;O_
zw&{m%+jFSPUE3HI%4fF99BQ&|S5*}p1%hoAY%7j<kp+0PNBpquwBjzPm~E(>9iMK=
z>a*<a3M60XG+<=qDF(W#p=}fugYDuP2i&rYvXpX{aoYk4a5zKBJdhyArxB})*+$A*
zMR!XLfUyk~=t*b`+fb3I27%N)Xg6j33t~qA<|oUmD{C}`*Ki(|Q!MUyEe_mix4rfe
zfVZaJ$q9vulA3_y>_OF?0xN)n#bMFU>erBd07N(Hq>k&Fg%ABRubV&(UB?ZrflXrJ
zIx%nqTbhAQJcccphc%0g5w&OHI<|;G$QR^3`P*F7F?$OfE>+nmEbMhfUQuKMh}2ab
uhuvl=wi&CJ5~W4|6bFkGpCfOoW5&@irrp4MM?I&s4#YqPR?~tIEbU)ev?d4u