def Mains(DirName,OutFile='Main.tex',mtype='pad',num=True,pyin=False):
txt_files={}
#print(OutFile)
fl=open(OutFile,'w',encoding='utf8')
fl.write(latexs[mtype]+'\n\n')
for root,dirs,files in os.walk(DirName):
for f in files:
if os.path.splitext(f)[1] in ['.txt']:
pf=root+'/'+f
if num:
fnum=re.findall('第(\d*)批',ut.ChNumToArab(f))
if len(fnum)==0:
txt_files[f]=Singal_input(pf,pyin)
else:
txt_files[fnum[0].zfill(3)]=Singal_input(pf,pyin)
else:
txt_files[f]=Singal_input(pf,pyin)
if len(txt_files)>0:
txt_files1=sorted(txt_files.items(),key=lambda txt_files:txt_files[0])
print(txt_files1)
for f in txt_files1:
print(f[0])
fl.write('\input{%s}'%f[1])
fl.write(r'\newpage')
#fl.write('\n\n')
fl.write(end)
fl.close()
#print('%s'%OutFile)
#p=subprocess.Popen('xelatex -no-pdf -interaction=nonstopmode %s' %OutFile, shell=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
#p=subprocess.Popen('xelatex -interaction=nonstopmode %s' %OutFile, shell=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
os.system('xelatex -no-pdf -interaction=nonstopmode %s' %OutFile)
os.system('xelatex -interaction=nonstopmode %s' %OutFile)
_removef(OutFile)
for root,dirs,files in os.walk(DirName):
for f in files:
if os.path.splitext(f)[1] in ['.tex']:
#os.system('rm %s'%os.path.abspath(root+'/'+f))
pass
return
def MainsGF(DirName,OutFile='Main',mtype='pad',num=None,\
pyin=False,Total='max',Research=None,\
startw=None,item1_bool=False,item2_bool=False,\
item0_bool=False):
txt_files={}
rsch=[]
if isinstance(Research,str):
rsch.append(Research)
elif isinstance(Research,list):
rsch.extend(Research)
for root,dirs,files in os.walk(DirName):
for f in files:
if os.path.splitext(f)[1].lower() in ['.txt','.doc','.docx']:
if sys.platform.startswith('win'):
rt1=root.split('\\')
root='/'.join(rt1)
pf=root+'/'+f
#print(pf)
if num is not None:
fnum=num.findall(ut.ChNumToArab(f))
if len(fnum)==0:
txt_files[f]=Singal_input(pf,pyin,item1_bool=item1_bool,item2_bool=item2_bool)
else:
txt_files[fnum[0].zfill(3)]=Singal_input(pf,pyin,item1_bool=item1_bool,item2_bool=item2_bool,item0_bool=item0_bool)
elif (num is None) and (Research is not None):
for i in rsch:
if i in f:
txt_files[f]=Singal_input(pf,pyin,item1_bool=item1_bool,item2_bool=item2_bool,item0_bool=item0_bool)
elif (num is None) and (startw is not None):
if startw.match(f) is not None:
txt_files[f]=Singal_input(pf,pyin,item1_bool=item1_bool,item2_bool=item2_bool,item0_bool=item0_bool)
else:
txt_files[f]=Singal_input(pf,pyin,item1_bool=item1_bool,item2_bool=item2_bool,item0_bool=item0_bool)
if len(txt_files)>0:
txt_files1=sorted(txt_files.items(),key=lambda txt_files:txt_files[0])
else:
print('No files 适合条件')
sys.exit()
#print(txt_files1)
##########################3
if Total=='max':
OutFile1=OutFile+'.tex'
fl=open(OutFile1,'w',encoding='utf8')
fl.write(latexs[mtype]+'\n\n')
for f in txt_files1:
fl.write('\input{%s}'%f[1])
fl.write(r'\newpage')
#fl.write('\n\n')
fl.write(end)
fl.close()
os.system('xelatex -no-pdf -interaction=nonstopmode %s' %OutFile1)
os.system('xelatex -interaction=nonstopmode %s' %OutFile1)
_removef(OutFile1)
###########################3
elif isinstance(Total,int):
for f in txt_files1:
txp=[txt_files1[i:i+Total] for i in range(0,len(txt_files),Total)]
fn=1
for ff in txp:
OutFile1=OutFile+'_%s.tex'%str(fn).zfill(2)
fl=open(OutFile1,'w',encoding='utf8')
fl.write(latexs[mtype]+'\n\n')
for f in ff:
fl.write('\input{%s}'%f[1])
fl.write(r'\newpage')
#fl.write('\n\n')
fl.write(end)
fl.close()
os.system('xelatex -no-pdf -interaction=nonstopmode %s' %OutFile1)
os.system('xelatex -interaction=nonstopmode %s' %OutFile1)
_removef(OutFile1)
fn +=1
else:
print('Total is max out int, please input the right parameter.')
for root,dirs,files in os.walk(DirName):
for f in files:
if os.path.splitext(f)[1] in ['.tex']:
os.remove('%s'%os.path.abspath(root+'/'+f))
pass
return
def Mains(DirName,OutFile='Main',mtype='pad',num=None,\
pyin=False,Total='max',\
item1_bool=False,item2_bool=False,\
item0_bool=False):
txt_files={}
for root,dirs,files in os.walk(DirName):
for f in files:
if os.path.splitext(f)[1].lower() in ['.txt','.doc','.docx']:
if sys.platform.startswith('win'):
rt1=root.split('\\')
root='/'.join(rt1)
pf=root+'/'+f
#print(pf)
if num is not None:
fnum=num.findall(ut.ChNumToArab(f))
if len(fnum)==0:
txt_files[f]=Singal_input(pf,pyin,item1_bool=item1_bool,item2_bool=item2_bool,item0_bool=item0_bool)
else:
txt_files[fnum[0].zfill(3)]=Singal_input(pf,pyin,item1_bool=item1_bool,item2_bool=item2_bool,item0_bool=item0_bool)
else:
txt_files[f]=Singal_input(pf,pyin,item1_bool=item1_bool,item2_bool=item2_bool,item0_bool=item0_bool)
if len(txt_files)>0:
txt_files1=sorted(txt_files.items(),key=lambda txt_files:txt_files[0])
print(txt_files1)
##########################3
if (Total=='max') or (len(txt_files)<Total):
OutFile1=OutFile+'.tex'
fl=open(OutFile1,'w',encoding='utf8')
fl.write(latexs[mtype]+'\n\n')
for f in txt_files1:
fl.write('\input{%s}'%f[1])
fl.write(r'\newpage')
#fl.write('\n\n')
fl.write(end)
fl.close()
os.system('xelatex -no-pdf -interaction=nonstopmode %s' %OutFile1)
os.system('xelatex -interaction=nonstopmode %s' %OutFile1)
#cmd=subprocess.Popen('xelatex -no-pdf -interaction=nonstopmode %s'%OutFile1,stdin=subprocess.PIPE,stdout=subprocess.PIPE,stderr=subprocess.PIPE, shell=True)
#cmd=subprocess.Popen('xelatex -interaction=nonstopmode %s'%OutFile1,stdin=subprocess.PIPE,stdout=subprocess.PIPE,stderr=subprocess.PIPE, shell=True)
_removef(OutFile1)
###########################3
elif isinstance(Total,int) and (len(txt_files)>Total):
txp=[txt_files1[i:i+Total] for i in range(0,len(txt_files),Total)]
#fn=1
for ii,ff in enumerate(txp):
OutFile1=OutFile+'_%s.tex'%str(ii).zfill(2)
fl=open(OutFile1,'w',encoding='utf8')
fl.write(latexs[mtype]+'\n\n')
for f in ff:
fl.write('\input{%s}'%f[1])
fl.write(r'\newpage')
fl.write('\n')
fl.write(end)
fl.close()
os.system('xelatex -no-pdf -interaction=nonstopmode %s' %OutFile1)
os.system('xelatex -interaction=nonstopmode %s' %OutFile1)
_removef(OutFile1)
#fn +=1
else:
print('Total is max out int, please input the right parameter.')
for root,dirs,files in os.walk(DirName):
for f in files:
if os.path.splitext(f)[1] in ['.tex']:
os.remove('%s'%os.path.abspath(root+'/'+f))
pass
return
def PdfFile(path,OutFile='Main',mtype='pad',\
num=None,pyin=False,Total='max',res=True,\
item1_bool=False,item2_bool=False,\
item0_bool=False):
file_list=[]
path_list=[]
if isinstance(path,list):
for f in path:
if os.path.isfile(f):
file_list.append(f)
elif os.path.isdir(f):
path_list.append(f)
elif os.path.isfile(path):
file_list.append(path)
elif os.path.isdir(path):
path_list.append(path)
elif path is None:
txtpath=os.getcwd()
else:
print('Please in list of dir/file,or dir,file')
sys.exit()
Tem_files_list=[]
if len(path_list)>0:
for path in path_list:
for root,ds,fs in os.walk(path):
for f in fs:
path=os.path.abspath(os.path.join(root,f))
Tem_files_list.append(path)
if len(file_list)>0:
for f in file_list:
Tem_files_list.append(os.path.abspath(f))
txt_files={}
for f in Tem_files_list:
f_name=os.path.basename(f)
if os.path.splitext(f)[1].lower() in ['.txt','.doc','.docx']:
if num is not None:
fnum=num.findall(ut.ChNumToArab(f_name))
if len(fnum)==0:
txt_files[f_name]=Singal_input(f,pyin,item1_bool=item1_bool,item2_bool=item2_bool,item0_bool=item0_bool)
else:
txt_files[fnum[0].zfill(3)]=Singal_input(f,pyin,item1_bool=item1_bool,item2_bool=item2_bool,item0_bool=item0_bool)
else:
txt_files[f_name]=Singal_input(f,pyin,item1_bool=item1_bool,item2_bool=item2_bool,item0_bool=item0_bool)
if len(txt_files)>0:
txt_files1=sorted(txt_files.items(),key=lambda txt:txt[0],reverse=res)
if Total=='max':
OutFile1=OutFile+'.tex'
fl=open(OutFile1,'w',encoding='utf8')
fl.write(latexs[mtype]+'\n\n')
for ff in txt_files1:
fl.write('\input{%s}'%ff[1])
fl.write(r'\newpage')
#fl.write('\n\n')
fl.write(end)
fl.close()
os.system('xelatex -no-pdf -interaction=nonstopmode %s' %OutFile1)
os.system('xelatex -interaction=nonstopmode %s' %OutFile1)
_removef(OutFile1)
###########################3
elif isinstance(Total,int):
for f in txt_files1:
txp=[txt_files1[i:i+Total] for i in range(0,len(txt_files),Total)]
fn=1
for ff in txp:
OutFile1=OutFile+'_%s.tex'%str(fn).zfill(2)
fl=open(OutFile1,'w',encoding='utf8')
fl.write(latexs[mtype]+'\n\n')
for f in ff:
fl.write('\input{%s}'%f[1])
fl.write(r'\newpage')
#fl.write('\n\n')
fl.write(end)
fl.close()
os.system('xelatex -no-pdf -interaction=nonstopmode %s' %OutFile1)
os.system('xelatex -interaction=nonstopmode %s' %OutFile1)
_removef(OutFile1)
fn +=1
else:
print('Total is max out int, please input the right parameter.')
for f in txt_files1:
#print(f[1])
os.remove(f[1])
pass
return
def GenerateBookGF(path,regrex1=None,\
search=None,startw=None,\
exclude=None,\
func=C2html,\
item1_bool=False,\
item2_bool=False,\
item0_bool=False,\
htmlfile='htmlfile/htmlbook_output',\
pdffile='htmlbook_Main',mtype='article',\
num=None,pyin=False,File_num='max',\
m1=re.compile(r'^第\w{1,3}[编|篇]'),\
m2=re.compile(r'^第\w{1,3}章'),\
m3=re.compile(r'^第\w{1,3}节'),\
m4=re.compile(r'^\w{1,3}、'),\
index=True,res=True,\
Spp=False,\
Spplit=False,\
rc=re.compile('(.*?案\s*（检例第\d*号）)'),\
p1=re.compile('【要\s*旨】'),p2=re.compile('【\w*】'),yz=True):
"""
regrex:re.compile('\d*'),从文件名中提取中关键字作排序用
search:str/list,民事诉讼，将文件名中符合含有关键字的文件提取出来
startw:re.compile('^ok')，将文件名中以特定字开头的文件提取出来
exclude:str/list,刑事诉讼，将含有exclude的文件予以排除
num:regrex的作用相同，主要是用于latex的文件中
m1:html文件中的一级目录
m2:同上，是2级目录g
m3:同上,是3级目录
m4:同上，是4级目录
"""
if func.__name__ in ['MainSpp']:
func(path,yz=yz,mtype=mtype)
return
if func.__name__ in ['MainsAbs']:
func(path,pyin=pyin,Startw=startw,mtype=mtype,regrex1=regrex1)
return
cc=re.compile('([，、:-》.《—_;；〈〉<>【】（）()])*\s*-')
rs=[]
if isinstance(search ,list):
rs.extend(search)
elif isinstance(search ,str):
rs.append(search)
excl=[]
if isinstance(exclude ,list):
excl.extend(exclude)
elif isinstance(exclude,str):
excl.append(exclude)
file_list = []
path_list = []
if isinstance(path,list):
for f in path:
if isfile(f):
file_list.append(f)
elif isdir(f):
path_list.append(f)
elif isfile(path):
file_list.append(path)
elif isdir(path):
path_list.append(path)
elif path is None:
txtpath = os.getcwd()
else:
print('Please in list of dir/file,or dir,file')
sys.exit()
File_tmp = GFlist(path_list)
for ff in File_tmp:
file_list.append(ff[1])
only_one = set()
fls = []
word = re.compile(r'[\u4e00-\u9fa5]+\d*')
for ff in file_list:
aa = os.path.basename(ff)
nwd = ''.join(word.findall(aa))
if nwd not in only_one:
only_one.add(nwd)
fls.append(ff)
if len(fls) > 0:
file_list = fls
temff = set()
if exclude is not None:
for ff in file_list:
for ex in excl:
if ex in os.path.basename(ff):
temff.add(ff)
File_tmp = [f for f in file_list if f not in temff]
Final_list = {}
for f in File_tmp:
ff=basename(f)
if regrex1 is not None:
if splitext(ff)[1].lower() in ['.txt','.doc','.docx']:
i1 = [i for i in regrex1.findall(ff) if len(i) > 0]
i2 = [i for i in regrex1.findall(ut.ChNumToArab(ff)) if len(i) > 0]
if len(i1) > 0:
num1 = int(i1[0])
Final_list[num1] = f
elif len(i2) > 0:
num1= int(i2[0])
Final_list[num1] = f
else:
num1 = cc.sub('', ff).replace(' ', '')
Final_list[num1] = f
if search is not None:
Tem={}
for k,v in Final_list.items():
for rsch in rs:
if rsch in basename(v):
Tem[k]=v
if len(Tem)>0:
Final_list=Tem
else:
print('没有关于 "%s" 的文件'%search)
sys.exit()
if startw is not None:
dff={}
for k,v in Final_list.items():
if startw.match(basename(v)) is not None:
#print('start word ...',v)
dff[k]=v
if len(dff)>0:
Final_list=dff
else:
print('没有符合的文件')
sys.exit()
if len(Final_list)>0:
Final=sorted(Final_list.items(),key=lambda item:item[0],reverse=res)
Final_files=[i[1] for i in Final]
#if res:
# Final_files
if func.__name__ in ['C2html','txt2htmlv1']:
func(Final_files,output=htmlfile,m1=m1,m2=m2,m3=m3,index=index)
pass
elif func.__name__ in ['PdfFile']:
func(Final_files,OutFile=pdffile,mtype=mtype,\
num=num,pyin=pyin,Total=File_num,\
item0_bool=item0_bool,\
item1_bool=item1_bool,item2_bool=item2_bool)
#os.remove(pdffile+'.pdf','htmlfile/'+pdffile+'.pdf')
pass
else:
print('Please input right function:','C2html','C2htmlBase','txt2htmlv1','txt2html_inonefile','PdfFile')
if Spplit:
shutil.rmtree(path)
return#Final_files
def GFlistv2(path,regrex1=None,research=None,startw=None,exclude=None,res=False):
"""
regrex1:为re.compile 的类型
startw:re.compile类型
research: str or list
exclude: str or list
"""
rs=[]
if isinstance(research ,list):
rs.extend(research)
elif isinstance(research ,str):
rs.append(research)
excl=[]
if isinstance(exclude ,list):
excl.extend(exclude)
elif isinstance(exclude,str):
excl.append(exclude)
pathlist=[]
filelist = []
if isinstance(path,list):
for ff in path:
if os.path.isfile(ff):
filelist.append(ff)
elif os.path.isdir(ff):
pathlist.append(ff)
elif isinstance(path,str):
if os.path.isdir(path):
pathlist.append(path)
ss={}
sre = re.compile('^(\d{4}-*\d{2}-*\d{2})')
for path in pathlist:
for root,ds,fs in os.walk(path):
for f in fs:
#print(f)
if regrex1 is not None:
#print('ok....1')
ff=os.path.splitext(f)[0].lower()
ff=sre.sub('',ff)
if os.path.splitext(f)[1].lower() in ['.txt','.doc','.docx']:
i1=[i for i in regrex1.findall(ff) if len(i)>0]
i2=[i for i in regrex1.findall(ut.ChNumToArab(ff)) if len(i)>0]
if len(i1)>0:
num=int(i1[0])
ss[num]=os.path.abspath(os.path.join(root,f))
elif len(i2)>0:
num= int(i2[0])
ss[num]=os.path.abspath(root+'/'+f)
#dd=sorted(ss.items(),key=lambda item:item[0])
else:
#print('ok ......2')
f1=os.path.splitext(f)[0]
num=cc.sub('',f1).replace(' ','')
ss[num]=os.path.abspath(root+'/'+f)
#dd=sorted(ss.items(),key=lambda item:item[0])
if (research is not None):
ddf={}
for k,v in ss.items():
for rsch in rs:
if rsch in os.path.basename(v):
ddf[k]=v
if len(ddf)>0:
ss=ddf
else:
print('没有关于 "%s" 的文件'%research)
return
if startw is not None:
dff={}
for k,v in ss.items():
name = os.path.basename(v)
if startw.match(v) is not None:
dff[k]=v
if len(dff)>0:
ss=dff
if exclude is not None:
File_tmp = {}
for k,v in ss.items():
for ex in excl:
if ex not in os.path.basename(v):
File_tmp[k] = v
ss=File_tmp
if len(ss)>0:
dd=sorted(ss.items(),key=lambda item:item[0], reverse=res)
return dd
else:
print('没有关于 "%s" 的文件'%research)
return
def GFlistv1(path,\
regrex1=None,\
search=None,\
startw=None,\
exclude=None,\
res=False):
"""
regrex1:为re.compile 的类型，选取相应的关键字作为排序
startw:re.compile类型，选取以某个字为开头
search: str or list
res:True or False,是否倒序
"""
rs=[]
if isinstance(search ,list):
rs.extend(search)
elif isinstance(search ,str):
rs.append(search)
file_list=[]
path_list=[]
if isinstance(path,list):
for f in path:
if os.path.isfile(f):
file_list.append(f)
elif os.path.isdir(f):
path_list.append(f)
elif os.path.isfile(path):
file_list.append(path)
elif os.path.isdir(path):
path_list.append(path)
elif path is None:
txtpath=os.getcwd()
excl=[]
if isinstance(exclude ,list):
excl.extend(exclude)
elif isinstance(exclude,str):
excl.append(exclude)
for path in path_list:
for root,ds,fs in os.walk(path):
for f in fs:
file_list.append(os.path.abspath(os.path.join(root,f)))
only_one=set()
fls=[]
word=re.compile(r'[\u4e00-\u9fa5]+')
for ff in file_list:
aa=os.path.basename(ff)
nwd=''.join(word.findall(aa))
if nwd not in only_one:
only_one.add(nwd)
fls.append(ff)
if len(fls)>0:
file_list=fls
temff=set()
if exclude is not None:
for ff in file_list:
for ex in excl:
aa=os.path.basename(ff)
if ex in aa:
temff.add(ff)
File_tmp=[f for f in file_list if f not in temff]
Final_list={}
for f in File_tmp:
ff=os.path.basename(f)
if regrex1 is not None:
if splitext(ff)[1].lower() in ['.txt','.doc','.docx']:
i1=[i for i in regrex1.findall(ff) if len(i)>0]
i2=[i for i in regrex1.findall(ut.ChNumToArab(ff)) if len(i)>0]
if len(i1)>0:
num1=int(i1[0])
Final_list[num1]=f
elif len(i2)>0:
num1= int(i2[0])
Final_list[num1]=f
else:
num1=cc.sub('',ff).replace(' ','')
Final_list[num1]=f
if search is not None:
Tem={}
for k,v in Final_list.items():
for rsch in rs:
if rsch in os.path.basename(v):
Tem[k]=v
if len(Tem)>0:
Final_list=Tem
else:
print('没有关于 "%s" 的文件'%search)
sys.exit()
if startw is not None:
dff={}
for k,v in Final_list.items():
if startw.match(basename(v)) is not None:
#print('start word ...',v)
dff[k]=v
if len(dff)>0:
Final_list=dff
else:
print('没有符合的文件')
sys.exit()
Final_files=[]
if len(Final_list)>0:
Final=sorted(Final_list.items(),key=lambda item:item[0],reverse=res)
Final_files=[i[1] for i in Final]
return Final_files
def GFlist(path,regrex1=None,research=None,startw=None):
"""
regrex1:为re.compile 的类型
startw:re.compile类型
research: str or list
"""
rs=[]
if isinstance(research ,list):
rs.extend(research)
elif isinstance(research ,str):
rs.append(research)
pathlist=[]
if isinstance(path,list):
pathlist.extend(path)
elif isinstance(path,str):
pathlist.append(path)
ss={}
for path in pathlist:
for root,ds,fs in os.walk(path):
for f in fs:
#print(f)
if regrex1 is not None:
#print('ok....1')
if os.path.splitext(f)[1].lower() in ['.txt','.doc','.docx']:
i1=[i for i in regrex1.findall(f) if len(i)>0]
i2=[i for i in regrex1.findall(ut.ChNumToArab(f)) if len(i)>0]
if len(i1)>0:
num=int(i1[0])
ss[num]=os.path.abspath(os.path.join(root,f))
elif len(i2)>0:
num= int(i2[0])
ss[num]=os.path.abspath(root+'/'+f)
dd=sorted(ss.items(),key=lambda item:item[0])
else:
#print('ok ......2')
num=cc.sub('',f).replace(' ','')
ss[num]=os.path.abspath(root+'/'+f)
dd=sorted(ss.items(),key=lambda item:item[0])
if (regrex1 is None) and (research is not None):
ddf={}
for k,v in dd:
for rsch in rs:
if rsch in k:
ddf[k]=v
if len(ddf)>0:
dd=sorted(ddf.items(),key=lambda item:item[0])
else:
print('没有关于 "%s" 的文件'%research)
if (regrex1 is None) and (startw is not None):
dff={}
for k,v in dd:
if startw.match(k) is not None:
dff[k]=v
if len(dff)>0:
dd=sorted(dff.items(),key=lambda item:item[0])
else:
print('没有关于 "%s" 的文件'%research)
return dd