From ee14e73411a720dd88d6cb1de300f39be85c1406 Mon Sep 17 00:00:00 2001
From: HuangHai <10402852@qq.com>
Date: Thu, 10 Jul 2025 15:36:20 +0800
Subject: [PATCH] 'commit'
---
dsLightRag/ShiTi/T3_DocxToMd.py | 3 ++-
dsLightRag/Util/DocxUtil.py | 10 ++++++++--
.../Util/__pycache__/DocxUtil.cpython-310.pyc | Bin 1365 -> 1467 bytes
dsLightRag/Word转试题.md | 2 +-
.../media/image1.png | Bin 0 -> 5807 bytes
5 files changed, 11 insertions(+), 4 deletions(-)
create mode 100644 dsLightRag/static/Images/3a5fa82d1a614209a8b81f9321b21808/media/image1.png
diff --git a/dsLightRag/ShiTi/T3_DocxToMd.py b/dsLightRag/ShiTi/T3_DocxToMd.py
index 307e15ab..b9805f06 100644
--- a/dsLightRag/ShiTi/T3_DocxToMd.py
+++ b/dsLightRag/ShiTi/T3_DocxToMd.py
@@ -7,7 +7,8 @@ async def main():
# 要处理的文件路径
file_path = "Docx/《动能定理》巩固练习.docx"
# 转换docx为md
- get_docx_content_by_pandoc(file_path, '../Word转试题.md',extract_media='../static/Images/')
+ get_docx_content_by_pandoc(file_path, '../Word转试题.md', parent_dir=True)
+
if __name__ == "__main__":
asyncio.run(main())
diff --git a/dsLightRag/Util/DocxUtil.py b/dsLightRag/Util/DocxUtil.py
index d5f1784f..a76fd99e 100644
--- a/dsLightRag/Util/DocxUtil.py
+++ b/dsLightRag/Util/DocxUtil.py
@@ -3,7 +3,7 @@ import subprocess
import uuid
-def get_docx_content_by_pandoc(docx_file, output_file=None, extract_media=None):
+def get_docx_content_by_pandoc(docx_file, output_file=None, parent_dir=None):
# 最后拼接的内容
content = ""
# output_file 设置为临时目录下的uuid.md
@@ -11,10 +11,16 @@ def get_docx_content_by_pandoc(docx_file, output_file=None, extract_media=None):
# 将docx_file去掉扩展名
prefix = docx_file.split(".")[0].split("/")[-1]
temp_markdown = os.path.join('./static/markdown/', prefix + '.md')
+ if parent_dir:
+ temp_markdown = os.path.join('../static/markdown/', prefix + '.md')
# 调用pandoc将docx文件转换成markdown
- if extract_media is None:
+ if parent_dir is None:
os.mkdir("./static/Images/" + file_name)
extract_media = "./static/Images/"
+ else:
+ os.mkdir("../static/Images/" + file_name)
+ extract_media = "../static/Images/"
+
subprocess.run(['pandoc', docx_file, '-f', 'docx', '-t', 'markdown', '-o', temp_markdown,
'--extract-media=' + extract_media + file_name])
# 读取然后修改内容,输出到新的文件
diff --git a/dsLightRag/Util/__pycache__/DocxUtil.cpython-310.pyc b/dsLightRag/Util/__pycache__/DocxUtil.cpython-310.pyc
index a7cd04bea90de30d8ec5665846fb7d2d08b75c60..044dab59cfe5a3271026a024304f9a29ee65d2aa 100644
GIT binary patch
delta 648
zcmZWn%We}f6tz80GUIvV(L!1X1qv0a1c_Jx8+Nc^frJDSA{0eK?oiS)nK0w1QLz
ziWNdo
{zm9!3VJ657_VxTu-3_Ve88G93Nj_ANia3>;{SN3xZ=SPM+Trhr#1|
zfXKtRg^@9KIJ-GdFG;>r$*W+i3e?)9V7jUpkSR&8NuJlhQ5;!H2{^hoc1lhhb3)go
zojc$v0v`AfKph&Y3QdKzjB48{&sy4+0{Ip!!SXxneXJej+$K-vPqk1YcMD?HEPA=sYG2vVxk0q8Eak&mn_zC?#TFjN_E2{gXumKR$R?~GpbE`zsjAVJ
z*I$6Of?*pMO&j;g=EmXyyRx~|?e;Pm%F(bFhv_aPd*j}Ihucxs+i!M1y=EcZ
z2>K2r!`a~3=tb0blc}6cWeL8ENti}sIe<~RaQWrHk7hCrhjI`{FbWsf`KwMJKN4qx
Xt*{p5v_)+e&?*fWr^{^dg@5=3k;kCZ
delta 525
zcmY*WO-md>5UuJN-T7W!SI6};noE{MNDks9w+LQE1#uH|Wj3p`iX6t49UxqUd^6uXxSt8~e`k0@t;G&+$(1``A49R*Nnphw}$#^B&LJ
z-#Y{?2&<8v7RZpg4;dnm5sS!3O)@2rMK(F)k|(>VD1{G-wQ1%&EiObB_j{<9N+;Us
zZfr(Sb7gSP5PP5+Wy=zq%#{HwaK#GojlAw1NvjLGM&vnQK0fuaBa
diff --git a/dsLightRag/Word转试题.md b/dsLightRag/Word转试题.md
index e738caeb..0123b7bb 100644
--- a/dsLightRag/Word转试题.md
+++ b/dsLightRag/Word转试题.md
@@ -1,6 +1,6 @@
【题型】不定项选择
【题文】如图所示,固定斜面倾角为*θ*,整个斜面分为*AB*、*BC*两段,*AB*=2*BC*.小物块*P*(可视为质点)与*AB*、*BC*两段斜面间的动摩擦因数分别为*μ*~1~、*μ*~2~.已知*P*由静止开始从*A*点释放,恰好能滑动到*C*点而停下,那么*θ*、*μ*~1~、*μ*~2~间应满足的关系是( )
-{width="0.9847222222222223in"
+{width="0.9847222222222223in"
height="0.6979166666666666in"}A.$tan\theta\text{=}\frac{\mu_{1} + 2\mu_{2}}{3}$
B.$tan\theta\text{=}\frac{2\mu_{1} + \mu_{2}}{3}$
C.$tan\theta\text{=}2\mu_{1} - \mu_{2}$
diff --git a/dsLightRag/static/Images/3a5fa82d1a614209a8b81f9321b21808/media/image1.png b/dsLightRag/static/Images/3a5fa82d1a614209a8b81f9321b21808/media/image1.png
new file mode 100644
index 0000000000000000000000000000000000000000..9e0e4c51a244d3e90b82d6ff1dee938f376207aa
GIT binary patch
literal 5807
zcmd^DcUMzSv<+RF2%$+41SA0|ia}bWcStT>iXb3L6NA)%6oV8&kt$L{5l8?9#o^z&Y9U~pR?xPi8Vp$u`=;7fj}Tu1AT2X5QrK8
zfv5^E&`=N|pPSDqFDhR%Jxx$~uKS7g98i(b8>QWadB~TbMx@<
z@bdCrzI>UFkB^_9UqC=WP*Cv7l`BF*Lc+qrSFc_b5fKp;6%`W`yLRoGxVSh30)axI
z5)u-Ul9Jc2Uzd`Sl9ra1k&%&=mA!G}#?6~I<>cgU-MR&X!Q|!TZ{NPHprD|rsHmi*
zq^zv0qM`za!|&X=qpGT^rlzK@uCAe>p{c2Cc{uWw*rU}$J)
zWMpJ)Y>Yr4kVqr|0463TrlzK5W@hH*<`xzfmX?-QR#tcK-nF*2wz09XwY9agv%7ci
zp1r-jgM-8U`}Z9k9i5zVPkii(Pkj*f|mdHM2XY;0^?T->WyuU@}?9UmY6=FOXg
zgoMPz#H6I8lw+7Zen{fB(L)u&}78sJOTohr{9V_>z*6($dnhva$~!K79Q6vAn#zqN3u{r%#_h
zf3B>o{O`a2s;a80tE+2jYQB8=Qd?VFS65eGU*FKs(Ae16)YR16+}zUA(%RbE*4Fm*
z>(_7JzJ34xy}iA?qobpgw9s+WPwX#>NJjOy1nw+}hgO-rnBX+1cIQ
z-P_yS-`_ttI5<2!JUTi$K0ZD~$y=U$U?82&oMiCh<=ZEjq
zppLj!wE***V5SphK;5wf1h*+A+#}P{q%pOo6lMOP18)4^U==ORIqjL>C@Nd3*5%&TJu?e_wcco9?dO48d}}_*K)PlJo!-
z6z#$1+()3q9d5Z@z=M91wRT|=Beqmjse|?^RvCUV8h6thzb9g{9z0D8{7Mpd5CH+~y(9ji
zyR%dPZur(r$?fC^ug_Y84ukd^$?!XstI3lrm
zYa)h#!TIPgT+aAO3{5kM5I%9BXq5|;^3Djh~9Y~$?ThTe=~mjZ*K@6>tJp(CGBTPd>C_EttU
z)`wghy8=pM>TTxlE;PtwHs^ICO)99!^L(xO+(yJ5A9)3h)ALN`Lw7vyvC{imM3=G2
zISzNg-!Y`pGICT=*kIgcXcDg24(5a(>WzA~4=Js#YFR}@Kq|PfkN%Ds=?YM5IYorNyJeriFG&9Lj=hez
z#XE9E;sy#(8^C)Co4x$Z2OZ*!lH-Lbxr^!r-96$IwMw1kcBeh^uwd==OR5THcdHer
z5D4G^YQ;VT68p@-1eE228-k?HV%Xjok+*-4tLPL45Zqtp84w9PIbS`a__pGPY6FKl
zCPLjA{J)a4bwX~hOw_WZ2V14)HNz&tr{cPZ@}fz(##&0>UFaBB^oVb9+rub^y8Frv
zFgq>ib8s<}3yr^oJ#L3v2Gd#bmr+4M5B<@U^Cw4B*K#
z@?w{rHsHY?exQ{aR4{7)6NPgo(F>&`P1<6vZ3rgi(kDEI>~q``bBn+sXZXTK-6G=N
zDQ^+UrfbWNiW-ctq+Dg)$E!tJjFLWj-jf$ji6c&HOA|CuI>bCKY?Ci+;kt=r=Cu0(
zKERL6k~*RodQv#)&oZ)XB;@VpE}|BHWw87#lp_@@j$YxbnBh^&EFL~z&MulH`Hc}*
zzNeUh&}K~4I2&ZiTv!O8yVKBH9D8OUyB?562Wuk+q~aCsMS?fV@VgT|pI(b^5gk(T
zfmtD)67tMTD%Bmwyxc_XurUUXU8Iqb;69y4tb*K!g4mNPc8Sc7l2eAUfX;bgQV=-H
zBeM(0N-P*Hrb3Vl*@Kz+!IV8STg@Z*255oGAr)(jD=SEjfrO1#qu_)93h6vTvN(DS
zi;Hu;esv8WXa|0nmF-~mmDmB#AkqT-#GNw+LbY0L0cWX)=0aaT)V}S9C5E058@$BV
zmc;F;1>Sv9$g6TRSTJ;22Q>MiOMDY2()RNivE$TZ{`reu2cK1r
zHp?*qHscB6TPa5B4KlL^V7NbP^|#q(SX+vg{xg}GU(rOh-Pe`FW9t+`jhcU)axTK!
z%wrT)q(@h|aE0gNJc?1nK^ZcH*rmW;(>>dA9>kDJ#f64)B5vr^D~UqIJ)!;R8U(%d
zvSNeJo}%Und!+k>Y7S{zvK-
zl0R%UVcR~-MCFIFFk&7OQ>$R>Tx-^OSZ-Q)r&utBLRW8fZJ771IJz>y|M+re5hHd?
zZz?$I>L2gkz~4>*nW)DUwUNBm(zkp{=0aS#9##ZJ<6=+dqaxaso2FQYS24#=;|)be
zeyD>F-D%BWs>UWO%egR&z_&+l=643;f)(g*7|1>{pvXmKywP{^w-46Lt)kq?{pyQC
zM{9;#!DM`!@%XD)L&4L7VOYRWRYc*#NG+AO`!B$CvhiXC1P+OVgITJf|8n0H(OE%sZ{u|gvRvxZKTlU
z8A1*&%DrH+jtKjO679MhbCOzN^Ydj<3b@bCqaVuKpo|!5poYf9d;q|3u5U?d-VE93
zE7^TIqc5c?LcVQFQu9a}4r-70Z3bVHyD<_)(TGZFmNP50UQMtI5V=@Qe=G(;mp;_F
z(qirt0m+CleDyII47VHKZ3-*%-ld(tt@wXI{h>vDLhqsqDQP(Q^%IDpPCmtYWOA-?{cF{ml!j{_`aG;1O0whm#{17vD34y@+JeBe|kc;_zEtPDdvN7k+pr|
z;^=`fUEYCs##?8{}{A&lofV`KUoK
z9Wdx63nRJDF1@I*wNLQ2s250{teM9xg)S_aJ?D=I$(|8OzM_f#V{UTevlVnXKLPpBNK%nh`6-b)eclk9N(MJS1(KoD3w{;Txs|$UDcT
zFPP1a^BpVa)+k?0oEEXp9BJ;5lH@0t;|MlnLV<#px{6A(0xm7FJT~Ya;Ft=8DD2
zDmAspJymRIa44D@?>;xQ--mvfYpsFbNg*n0tktFL
zm4UYe3GZXh+L>&bl{Eo}ESyKC*}@YnQC}tG$}QQSDH`^1x$CVG==pF)tJkQ*uGwq1
z==sDT-S*Lw;l(|R5O8J${IW~aIP~X(7AT+#YZt2d0d~3%sF3|Wev
z0SyoP1FiReA62nTB>GxLS)}Be9o>}5PKZ+(t?=2MR=WWs)(Z#7rLimjCe
z1rPdFc#~5nXnwJ{*=~qsJAAI#yt5lHcoQWL1hTawetEfX4TJ`jf@OI}Rn!*XI;|L-
z!*2Pfc`uCxrGncYb8k?c<_)@{Ne5S^B!OfDYzM2GYv1CW1i{@C+r7Ce;99Yewe8ZB
zWItWT$M3ahY!Kk&FwfY72KSPN6!?nKu`dTDZTQFY0Y6w7ITsMxE3J
z@ZDqwQCM>e4XX;#6zS6TZ=i8?rJ|EF$Fcn+YiX3kaD0(n%th<~G$iM%`z9vQ`Ln2|O
z#P~sj>HF=SAHF5D{!6iYgg2ZM#xJ%xsYPad(jhq<);7=^Fkohf8sNsDV4YoXol?t!
z>7-mfrvhw^JU|CHSFkBktHd6M%#jALWe?jvnP48lEw7Nx_F4b^KSc4Sv;OTgU$L={
zD<1y+9(g}#*3UIMHn<=F&d6xkxDXb^{YM9;5rsB0!sKJ9o6sDN?Bj+Ie1%jMK>yqY
zIgp6cj)+^rqKb_6Hzl#H5-D`d+i7qeOx$eYdxK$hObVS)oiA)bf+e*d0XZsu;QKYc
zE!X~pGrf#`FPLs@%dhc9(ABGEJ&{@yK>#&SLDz*0rk9fD-{uUVQCJP{C8;Jody`y3
z@J%z68~!56c|E`WM3uq1`+6xO-IwY+)|=&*(@paH!-8d{I~2dbE$dh>t#RU+UMuHZ
zI9p1s7s^}Hc3O0%JK7doEN`7uY~W&O+-#kMzwNg;G6`<$U4%
zZNp@tQ(O}+X@tx@Q}xW^RgvgV!o5E3Y2dYVP?2a@lCw-QSil`ugTwWxN}4bbUI}yI
z>_&=A2;DX?i?w88pLwGo>pk7*4T$KMH2V9u(?#}Fjeif>bR=>8x9A4(OXFu(j9X`J
zC7IlkrKgwTHFnbQml{qb(;}x`y1%7VqEyup!1*2MF`iwNyBW||4u$N`xmLO!=NoCOh(F7JzVXL6;${-2&mMx
zUgmlZX|l5Jrrfi9VCN2|n>MK6N~@$Mi+M&yIZ&YoJ)?>~fZzl^r~JDh?2fII#Q$5j
bb1MEfV$Vv7ja@01U?2k>q;|QcW5oXeDv