#!/usr/bin/python3
# -*- coding: UTF-8 -*-

##https://www.pianshen.com/article/5314917437/
##https://zhuanlan.zhihu.com/p/366902690
##https://itpcb.com/a/277599
import docxtpl
from docx.shared import Mm
from docxtpl import DocxTemplate,RichText
import pandas as pd
from pandas import DataFrame
import re
import sys
import os
import json
import time

if len(sys.argv) != 5:
    print(" ".join(['usage:python',sys.argv[0],'output_dir','tumor','sample_type(t for tissue,c for cfdna)']),'projcet')
    sys.exit()


output_dir=sys.argv[1]
name=sys.argv[2]
Sample_type=sys.argv[3]
projcet=sys.argv[4]
snv_base="".join([name,'.snvindel.pos.dedup.txt'])
snv_file='/'.join([output_dir,'mutation',snv_base])
snv_base_vus="".join([name,'.snvindel.vus.txt'])
snv_file_vus='/'.join([output_dir,'mutation',snv_base_vus])
fusion_base="".join([name,'.fusion.pos.dedup.txt'])
fusion_file='/'.join([output_dir,'fusion',fusion_base])
cnv_base="".join([name,'.cnv.pos.dedup.txt'])
cnv_file='/'.join([output_dir,'cnvkit',cnv_base])
qc_base=''.join([name,'_qc.txt'])
qc_file='/'.join([output_dir,'qc',qc_base])
report_base="".join([name,'_report.docx'])
report_file='/'.join([output_dir,'report',report_base])
indication_file="".join([output_dir,'/mutation/','indication.txt'])

context = {'list1':[],'list2':{},'list3':{},'clingene1':[],'clingene2':[],'nonclingenes':[],'genefunc':{},
'indication':[],'mmr':[],'chemo':[]}


#genefunction
genefunction={}
gf=open("/dataseq/jmdna/codes/reportbase/gene_function.txt",'r',encoding='utf-8').readlines()
for line in gf[1:]:
    gene=line.strip().split("\t")[0]
    func=line.strip().split("\t")[1]
    genefunction[gene.upper()]=func

##sensitive_resistant_drug
drug_disease={}
drug_mechanism={}
drug_fh=open("/dataseq/jmdna/codes/reportbase/target_drug.txt",'r',encoding='utf-8').readlines()
for line in drug_fh[1:]:
    disease=line.split("\t")[8]
    mechanism=line.split("\t")[11]
    drugs=line.split("\t")[0].split('|')
    if disease or mechanism:
        for drug in drugs:
            drug_disease[drug.upper()]=disease
            drug_mechanism[drug.upper()]=mechanism

       
sensitive_resistant_drug=[{'type':'可能敏感药物','drug':[]},{'type':'可能耐药药物','drug':[]}]
    
##somatic snvindel处理
snv_size = os.path.getsize(snv_file)
if snv_size>0:
    snv=pd.read_table(snv_file,sep="\t")
    cols=[index for index,row in snv[snv['可信']==0].iterrows()]
    snv.drop(cols,inplace=True)    
    genes=snv['Gene.refGene'].drop_duplicates()
    if len(genes):
      for gene in genes:
        rt={}
        rt[gene]=[]
        muts=snv['AAChange.refGene'][snv['Gene.refGene']==gene].drop_duplicates()
        for mut in muts:
            info2={mut:[]}
            for index,row in snv[snv['AAChange.refGene']==mut].iterrows():    
                info3={}
                info3['drug']=row['药物中文名']
                info3['effect']=row['Response_Type_C']
                info3['tumor']=row['疾病中文名']
                info3['evidence']=row['Evidence_Source_C']
                info3['sig']=row['EfficacyEvidence']
                info2[mut].append(info3)
##sensitive_resistant_drug
                drugs=row['Drug'].replace(" + ",",")
                drugs=drugs.split(",")
                drugs_chinese=row['药物中文名'].replace(" + ",",")
                drugs_chinese=drugs_chinese.split(",")
                bool=0
                for drug in drugs:
                    if drug.upper() in drug_disease.keys():
                        if re.search(r'敏感',row['Response_Type_C']):
                            sensitive_drug={}
                            sensitive_drug['name']=drugs_chinese[bool]                    
                            sensitive_drug['mechanism']=("\n".join([drug_disease[drug.upper()],drug_mechanism[drug.upper()]])).strip()
                            if sensitive_drug not in sensitive_resistant_drug[0]['drug']:
                                sensitive_resistant_drug[0]['drug'].append(sensitive_drug)
                        elif re.search(r'耐药',row['Response_Type_C']): 
                            resistant_drug={}
                            resistant_drug['name']=drugs_chinese[bool]
                            resistant_drug['mechanism']=("\n".join([drug_disease[drug.upper()],drug_mechanism[drug.upper()]])).strip()
                            if resistant_drug not in sensitive_resistant_drug[1]['drug']:
                                sensitive_resistant_drug[1]['drug'].append(resistant_drug)
                    bool+=1                            
            context['list2'][mut]=info2[mut]
            info={}
            info['gene']=snv['Gene.refGene'][snv['AAChange.refGene']==mut].reset_index(drop=True)[0]
            m=re.search(r'(p\..*)$',mut)
            if m:
                info['p']=m.group(1)
            else:
                m=re.search(r'(c\..*)$',mut)
                info['p']=m.group(1)
            info['freq']=snv['Freq'][snv['AAChange.refGene']==mut].reset_index(drop=True)[0]
            A=[]
            B=[]
            C=[]
            D=[]  			
            for index,row in snv[(snv['AAChange.refGene']==mut) & (snv['标签']=='适应症') & snv['Response_Type_C'].str.contains("敏感")].iterrows():
                ds=row['药物中文名'].split(",")
                evidence='A'
                ds_new=[str(x) + '【' + evidence + ' 级】'for x in ds]
                A.extend(ds_new)			
            for index,row in snv[(snv['AAChange.refGene']==mut) & (snv['标签']=='非适应症') & snv['Response_Type_C'].str.contains("敏感")].iterrows():
                ds=row['药物中文名'].split(",")
                evidence='C'
                ds_new=[str(x) + '【' + evidence + ' 级】'for x in ds]
                B.extend(ds_new)				
            for index,row in snv[(snv['AAChange.refGene']==mut) & (snv['标签']=='.') & snv['Response_Type_C'].str.contains("敏感")].iterrows():
                ds=row['药物中文名'].split(",")
                evidence=row['证据等级']
                ds_new=[str(x) + '【' + evidence + ' 级】'for x in ds]
                C.extend(ds_new)
            for index,row in snv[(snv['AAChange.refGene']==mut) & snv['Response_Type_C'].str.contains("耐药")].iterrows():
                evidence=''
                if row['标签']=='非适应症':
                    evidence='C'
                else:
                    evidence=row['证据等级']				
                ds=row['药物中文名'].split(",")
                ds_new=[str(x) + '【' + evidence + ' 级】'for x in ds]
                D.extend(ds_new)
            A=sorted(set(A),key=A.index)
            B=sorted(set(B),key=B.index)
            C=sorted(set(C),key=C.index)
            D=sorted(set(D),key=D.index)            
            info['drug_A']="\n".join(A)
            info['drug_B']="\n".join(B)
            info['drug_C']="\n".join(C)
            info['drug_D']="\n".join(D)
            if not info['drug_A']:
                info['drug_A']='/'
            if not info['drug_B']:
                info['drug_B']='/'
            if not info['drug_C']:
                info['drug_C']='/'
            if not info['drug_D']:
                info['drug_D']='/'
            context['list1'].append(info)
            rt[gene].append("".join([info['p'],'(',info['freq'],')']))
##genefunc            
            context['genefunc'][mut]=genefunction[gene.upper()]          
##clingenes            
            clingene1={}
            clingene2={}            
            for index,row in snv[(snv['AAChange.refGene']==mut)].iterrows():
                if row['标签']=='适应症' or row['证据等级']=='B':
                    clingene1['freq']=snv['Freq'][snv['AAChange.refGene']==mut].reset_index(drop=True)[0]
                    if len((snv['AAChange.refGene'][snv['AAChange.refGene']==mut].reset_index(drop=True)[0]).split(":")) == 5:
                        (clingene1['gene'],clingene1['transcript'],clingene1['exon'],clingene1['nacid'],clingene1['aacid'])=(snv['AAChange.refGene'][snv['AAChange.refGene']==mut].reset_index(drop=True)[0]).split(":")
                    else:
                        (clingene1['gene'],clingene1['transcript'],clingene1['exon'],clingene1['nacid'])=(snv['AAChange.refGene'][snv['AAChange.refGene']==mut].reset_index(drop=True)[0]).split(":")
                        clingene1['aacid'] = '/'
                    clingene1['muttype']=snv['ExonicFunc.refGene'][snv['AAChange.refGene']==mut].reset_index(drop=True)[0]
                    if re.match("nonsynonymous SNV",clingene1['muttype']):
                        clingene1['muttype']='错义突变'
                    elif re.search("^frameshift",clingene1['muttype']):
                        clingene1['muttype']='移码突变'
                    elif re.search("^nonframeshift",clingene1['muttype']):
                        clingene1['muttype']='非移码突变'
                    elif re.match("stopgain",clingene1['muttype']):
                        clingene1['muttype']='提前终止'
                    else:
                        clingene1['muttype']='/'
                    context['clingene1'].append(clingene1)
                else:
                    clingene2['freq']=snv['Freq'][snv['AAChange.refGene']==mut].reset_index(drop=True)[0]
                    if len((snv['AAChange.refGene'][snv['AAChange.refGene']==mut].reset_index(drop=True)[0]).split(":")) == 5:
                        (clingene2['gene'],clingene2['transcript'],clingene2['exon'],clingene2['nacid'],clingene2['aacid'])=(snv['AAChange.refGene'][snv['AAChange.refGene']==mut].reset_index(drop=True)[0]).split(":")
                    else:
                        (clingene2['gene'],clingene2['transcript'],clingene2['exon'],clingene2['nacid'])=(snv['AAChange.refGene'][snv['AAChange.refGene']==mut].reset_index(drop=True)[0]).split(":")
                        clingene2['aacid'] = '/'
                    clingene2['muttype']=snv['ExonicFunc.refGene'][snv['AAChange.refGene']==mut].reset_index(drop=True)[0]
                    if re.match("nonsynonymous SNV",clingene2['muttype']):
                        clingene2['muttype']='错义突变'
                    elif re.search("^frameshift",clingene2['muttype']):
                        clingene2['muttype']='移码突变'
                    elif re.search("^nonframeshift",clingene2['muttype']):
                        clingene2['muttype']='非移码突变'
                    elif re.match("stopgain",clingene2['muttype']):
                        clingene2['muttype']='提前终止'
                    else:
                        clingene2['muttype']='/'
                    context['clingene2'].append(clingene2)						
                break                
        context['list3'][gene]="\n".join(rt[gene])
    else:     
      snv_size=0


##target vus and nontarget vus

snv_size_vus = os.path.getsize(snv_file_vus)
if snv_size_vus>0:
    snv_vus=pd.read_table(snv_file_vus,sep="\t")
    for index,row in snv_vus.iterrows():
        if float(row['Freq'].replace('%',''))>=2:
            nonclingene={}
            if len(row['AAChange.refGene'].split(":")) == 5:
                (nonclingene['gene'],nonclingene['transcript'],nonclingene['exon'],nonclingene['nacid'],nonclingene['aacid'])=row['AAChange.refGene'].split(":")
            else:
                (nonclingene['gene'],nonclingene['transcript'],nonclingene['exon'],nonclingene['nacid'])=row['AAChange.refGene'].split(":")
                nonclingene['aacid'] = '/'
            nonclingene['freq']=row['Freq']
            nonclingene['muttype']=row['ExonicFunc.refGene']
            if re.match("nonsynonymous SNV",nonclingene['muttype']):
                nonclingene['muttype']='错义突变'
            elif re.search("^frameshift",nonclingene['muttype']):
                nonclingene['muttype']='移码突变'
            elif re.search("^nonframeshift",nonclingene['muttype']):
                nonclingene['muttype']='非移码突变'
            elif re.match("stopgain",nonclingene['muttype']):
                nonclingene['muttype']='提前终止'
            else:
                nonclingene['muttype']='/'
            context['nonclingenes'].append(nonclingene)   
 

##fusion处理
fusion_size = os.path.getsize(fusion_file)
if fusion_size>0:
    fusion=pd.read_table(fusion_file,sep="\t")
    cols=[index for index,row in fusion[fusion['可信']==0].iterrows()]
    fusion.drop(cols,inplace=True)
    genes=fusion['Gene_Symbol'].drop_duplicates()
    if len(genes):
      for gene in genes:
        rt={}
        rt[gene]=[]
        fusions=fusion['FUSION'][fusion['Gene_Symbol']==gene].drop_duplicates()
        for mut in fusions:
            info2={mut:[]}
            for index,row in fusion[fusion['FUSION']==mut].iterrows():    
                info3={}
                info3['drug']=row['药物中文名']
                info3['effect']=row['Response_Type_C']
                info3['tumor']=row['疾病中文名']
                info3['evidence']=row['Evidence_Source_C']
                info3['sig']=row['EfficacyEvidence']
                info2[mut].append(info3)
##sensitive_resistant_drug
                drugs=row['Drug'].replace(" + ",",")
                drugs=drugs.split(",")
                drugs_chinese=row['药物中文名'].replace(" + ",",")
                drugs_chinese=drugs_chinese.split(",")
                bool=0
                for drug in drugs:
                    if drug.upper() in drug_disease.keys():
                        if re.search(r'敏感',row['Response_Type_C']):
                            sensitive_drug={}
                            sensitive_drug['name']=drugs_chinese[bool]                    
                            sensitive_drug['mechanism']=("\n".join([drug_disease[drug.upper()],drug_mechanism[drug.upper()]])).strip()
                            if sensitive_drug not in sensitive_resistant_drug[0]['drug']:
                                sensitive_resistant_drug[0]['drug'].append(sensitive_drug)
                        elif re.search(r'耐药',row['Response_Type_C']): 
                            resistant_drug={}
                            resistant_drug['name']=drugs_chinese[bool]
                            resistant_drug['mechanism']=("\n".join([drug_disease[drug.upper()],drug_mechanism[drug.upper()]])).strip()
                            if resistant_drug not in sensitive_resistant_drug[1]['drug']:
                                sensitive_resistant_drug[1]['drug'].append(resistant_drug)
                    bool+=1  
            context['list2'][mut]=info2[mut]
            info={}
            info['gene']=mut
            info['p']='融合'
            info['freq']="".join([str(fusion['FREQ1'][fusion['FUSION']==mut].reset_index(drop=True)[0]),'%'])
            A=[]
            B=[]
            C=[]
            D=[]  			
            for index,row in fusion[(fusion['FUSION']==mut) & (fusion['标签']=='适应症') & fusion['Response_Type_C'].str.contains("敏感")].iterrows():
                ds=row['药物中文名'].split(",")
                evidence='A'
                ds_new=[str(x) + '【' + evidence + ' 级】'for x in ds]
                A.extend(ds_new)			
            for index,row in fusion[(fusion['FUSION']==mut) & (fusion['标签']=='非适应症') & fusion['Response_Type_C'].str.contains("敏感")].iterrows():
                ds=row['药物中文名'].split(",")
                evidence='C'
                ds_new=[str(x) + '【' + evidence + ' 级】'for x in ds]
                B.extend(ds_new)				
            for index,row in fusion[(fusion['FUSION']==mut) & (fusion['标签']=='.') & fusion['Response_Type_C'].str.contains("敏感")].iterrows():
                ds=row['药物中文名'].split(",")
                evidence=row['证据等级']
                ds_new=[str(x) + '【' + evidence + ' 级】'for x in ds]
                C.extend(ds_new)
            for index,row in fusion[(fusion['FUSION']==mut) & fusion['Response_Type_C'].str.contains("耐药")].iterrows():
                evidence=''
                if row['标签']=='非适应症':
                    evidence='C'
                else:
                    evidence=row['证据等级']				
                ds=row['药物中文名'].split(",")
                ds_new=[str(x) + '【' + evidence + ' 级】'for x in ds]
                D.extend(ds_new)
            A=sorted(set(A),key=A.index)
            B=sorted(set(B),key=B.index)
            C=sorted(set(C),key=C.index)
            D=sorted(set(D),key=D.index) 
            info['drug_A']="\n".join(A)
            info['drug_B']="\n".join(B)
            info['drug_C']="\n".join(C)
            info['drug_D']="\n".join(D)
#            info['drug_A']="\n".join(list(set(fusion['药物中文名'][(fusion['FUSION']==mut) & (fusion['标签']=='适应症') & fusion['Response_Type_C'].str.contains("敏感")].str.cat(sep=",").split(","))))
#            info['drug_B']="\n".join(list(set(fusion['药物中文名'][(fusion['FUSION']==mut) & (fusion['标签']=='非适应症') & fusion['Response_Type_C'].str.contains("敏感")].str.cat(sep=",").split(","))))
#            info['drug_C']="\n".join(list(set(fusion['药物中文名'][(fusion['FUSION']==mut) & (fusion['标签']=='.') & fusion['Response_Type_C'].str.contains("敏感")].str.cat(sep=",").split(","))))
#            info['drug_D']="\n".join(list(set(fusion['药物中文名'][(fusion['FUSION']==mut) & fusion['Response_Type_C'].str.contains("耐药")].str.cat(sep=",").split(","))))
            if not info['drug_A']:
                info['drug_A']='/'
            if not info['drug_B']:
                info['drug_B']='/'
            if not info['drug_C']:
                info['drug_C']='/'
            if not info['drug_D']:
                info['drug_D']='/'    
            context['list1'].append(info)
            rt[gene].append("".join([info['gene'],'(',info['freq'],')']))
##genefunc            
            context['genefunc'][mut]=genefunction[gene.upper()]
##clingenes
            clingene1={}
            clingene2={}            
            for index,row in fusion[(fusion['FUSION']==mut)].iterrows():
                if row['标签']=='适应症' or row['证据等级']=='B':            
                    clingene1['gene']= info['gene']
                    clingene1['freq']= info['freq']
                    (clingene1['transcript'],clingene1['exon'],clingene1['nacid'],clingene1['aacid'])=("/","/","/","/")
                    clingene1['muttype']= '融合'
                    context['clingene1'].append(clingene1)
                else:
                    clingene2['gene']= info['gene']
                    clingene2['freq']= info['freq']
                    (clingene2['transcript'],clingene2['exon'],clingene2['nacid'],clingene2['aacid'])=("/","/","/","/")
                    clingene2['muttype']= '融合'
                    context['clingene2'].append(clingene2)            
        context['list3'][gene]="\n".join(rt[gene])
    else:
      fusion_size=0


##cnv处理
cnv_size = os.path.getsize(cnv_file)
if cnv_size>0:
    cnv=pd.read_table(cnv_file,sep="\t")
    cols=[index for index,row in cnv[cnv['可信']==0].iterrows()]
    cnv.drop(cols,inplace=True)
    genes=cnv['gene'].drop_duplicates()
    if len(genes):
      for gene in genes:
        rt={}
        rt[gene]=[]
        cnvs=cnv['Gene_Symbol'][cnv['gene']==gene].drop_duplicates()
        for mut in cnvs:
            info={}
            info['gene']=mut
            copy=cnv['cn'][cnv['Gene_Symbol']==mut].reset_index(drop=True)[0]
            if copy > 2:
                info['p']='扩增'
            else:
                info['p']='缺失'
            A=[]
            B=[]
            C=[]
            D=[]  			
            for index,row in cnv[(cnv['Gene_Symbol']==mut) & (cnv['标签']=='适应症') & cnv['Response_Type_C'].str.contains("敏感")].iterrows():
                ds=row['药物中文名'].split(",")
                evidence='A'
                ds_new=[str(x) + '【' + evidence + ' 级】'for x in ds]
                A.extend(ds_new)			
            for index,row in cnv[(cnv['Gene_Symbol']==mut) & (cnv['标签']=='非适应症') & cnv['Response_Type_C'].str.contains("敏感")].iterrows():
                ds=row['药物中文名'].split(",")
                evidence='C'
                ds_new=[str(x) + '【' + evidence + ' 级】'for x in ds]
                B.extend(ds_new)				
            for index,row in cnv[(cnv['Gene_Symbol']==mut) & (cnv['标签']=='.') & cnv['Response_Type_C'].str.contains("敏感")].iterrows():
                ds=row['药物中文名'].split(",")
                evidence=row['证据等级']
                ds_new=[str(x) + '【' + evidence + ' 级】'for x in ds]
                C.extend(ds_new)
            for index,row in cnv[(cnv['Gene_Symbol']==mut) & cnv['Response_Type_C'].str.contains("耐药")].iterrows():
                evidence=''
                if row['标签']=='非适应症':
                    evidence='C'
                else:
                    evidence=row['证据等级']				
                ds=row['药物中文名'].split(",")
                ds_new=[str(x) + '【' + evidence + ' 级】'for x in ds]
                D.extend(ds_new)
            A=sorted(set(A),key=A.index)
            B=sorted(set(B),key=B.index)
            C=sorted(set(C),key=C.index)
            D=sorted(set(D),key=D.index) 
            info['drug_A']="\n".join(A)
            info['drug_B']="\n".join(B)
            info['drug_C']="\n".join(C)
            info['drug_D']="\n".join(D)
            info['freq']=" ".join([str(copy),'拷贝'])
#            info['drug_A']="\n".join(list(set(cnv['药物中文名'][(cnv['Gene_Symbol']==mut) & (cnv['标签']=='适应症') & cnv['Response_Type_C'].str.contains("敏感")].str.cat(sep=",").split(","))))
#            info['drug_B']="\n".join(list(set(cnv['药物中文名'][(cnv['Gene_Symbol']==mut) & (cnv['标签']=='非适应症') & cnv['Response_Type_C'].str.contains("敏感")].str.cat(sep=",").split(","))))
#            info['drug_C']="\n".join(list(set(cnv['药物中文名'][(cnv['Gene_Symbol']==mut) & (cnv['标签']=='.') & cnv['Response_Type_C'].str.contains("敏感")].str.cat(sep=",").split(","))))
#            info['drug_D']="\n".join(list(set(cnv['药物中文名'][(cnv['Gene_Symbol']==mut) & cnv['Response_Type_C'].str.contains("耐药")].str.cat(sep=",").split(","))))
            if not info['drug_A']:
                info['drug_A']='/'
            if not info['drug_B']:
                info['drug_B']='/'
            if not info['drug_C']:
                info['drug_C']='/'
            if not info['drug_D']:
                info['drug_D']='/'
            context['list1'].append(info)
            info2={mut:[]}
            for index,row in cnv[cnv['Gene_Symbol']==mut].iterrows():    
                info3={}
                info3['drug']=row['药物中文名']
                info3['effect']=row['Response_Type_C']
                info3['tumor']=row['疾病中文名']
                info3['evidence']=row['Evidence_Source_C']
                info3['sig']=row['EfficacyEvidence']
                info2[mut].append(info3)
##sensitive_resistant_drug
                drugs=row['Drug'].replace(" + ",",")
                drugs=drugs.split(",")
                drugs_chinese=row['药物中文名'].replace(" + ",",")
                drugs_chinese=drugs_chinese.split(",")
                bool=0
                for drug in drugs:
                    if drug.upper() in drug_disease.keys():
                        if re.search(r'敏感',row['Response_Type_C']):
                            sensitive_drug={}
                            sensitive_drug['name']=drugs_chinese[bool]                    
                            sensitive_drug['mechanism']=("\n".join([drug_disease[drug.upper()],drug_mechanism[drug.upper()]])).strip()
                            if sensitive_drug not in sensitive_resistant_drug[0]['drug']:
                                sensitive_resistant_drug[0]['drug'].append(sensitive_drug)
                        elif re.search(r'耐药',row['Response_Type_C']): 
                            resistant_drug={}
                            resistant_drug['name']=drugs_chinese[bool]
                            resistant_drug['mechanism']=("\n".join([drug_disease[drug.upper()],drug_mechanism[drug.upper()]])).strip()
                            if resistant_drug not in sensitive_resistant_drug[1]['drug']:
                                sensitive_resistant_drug[1]['drug'].append(resistant_drug)
                    bool+=1      
            rt[gene].append("".join([info['p'],'(',info['freq'],')']))
            context['list2'][" ".join([mut,info['p']])]=info2[mut]
##genefunc            
            context['genefunc'][" ".join([mut,info['p']])]=genefunction[mut.upper()]
##clingenes            
            clingene1={}
            clingene2={}            
            for index,row in cnv[(cnv['Gene_Symbol']==mut)].iterrows():
                if row['标签']=='适应症' or row['证据等级']=='B': 
                   clingene1['gene']=info['gene']
                   clingene1['freq']= info['freq']
                   (clingene1['transcript'],clingene1['exon'],clingene1['nacid'],clingene1['aacid'])=("/","/","/","/")
                   clingene1['muttype']= info['p']
                   context['clingene1'].append(clingene1)
                else:
                   clingene2['gene']=info['gene']
                   clingene2['freq']= info['freq']
                   (clingene2['transcript'],clingene2['exon'],clingene2['nacid'],clingene2['aacid'])=("/","/","/","/")
                   clingene2['muttype']= info['p']
                   context['clingene2'].append(clingene2) 
        context['list3'][gene]="\n".join(rt[gene])
    else:
      cnv_size=0


##msi
if Sample_type == 't':
    msi_file=''.join([output_dir,'/MSI/',name,'.msi'])
    msi=(open(msi_file,'r').readlines()[1]).split("\t")
    context['msi_count']=msi[0]
    context['msi_value']=round(float(msi[2].strip())/100,2)
    if context['msi_value']>=0.3:
        context['msi_result']='MSI-H'
        context['msi_predict']='对免疫检查点抑制剂可能敏感'
    else:
        context['msi_result']='MSS'
        context['msi_predict']='对免疫检查点抑制剂可能不敏感'


##MMR处理
mmr_file=''.join([output_dir,'/MMR/',name,"_mmr.txt"])
mmr_size = os.path.getsize(mmr_file)
mmr_result=0
mmr_result_summary=[]
if mmr_size>0:
    mmr_fh=open(mmr_file,'r',encoding='utf-8').readlines()
    for line in mmr_fh[1:]:
        mmr={}
        mmr['gene']= line.strip().split("\t")[0]
        mmr['transcript'] = line.strip().split("\t")[1]
        mmr['nacid'] = line.strip().split("\t")[2]
        mmr['aacid'] = line.strip().split("\t")[3]
        mmr['muttype'] = line.strip().split("\t")[5]    
        mmr['freq'] = line.strip().split("\t")[4]
        mmr['sig'] = line.strip().split("\t")[6]
        if mmr['sig'] != '意义未明突变':
            mmr_result+=1
            mmr_result_summary.append(mmr['gene'] + ' ' + mmr['aacid']) 
        context['mmr'].append(mmr)

context['mmr_result']=mmr_result
mmr_result_summary=' | '.join(mmr_result_summary)
if mmr_result_summary:
    context['mmr_result_summary']=mrr_result_summary
    context['mmr_predict']="对免疫检查点抑制剂可能敏感"
else:
    context['mmr_result_summary']="未检测到相关基因突变"
    context['mmr_predict']="对免疫检查点抑制剂可能不敏感"



##chemo
chemo_file=''.join([output_dir,'/chemo/',name,".drug.res.txt"])
chemo_fh=open(chemo_file,'r')
bool=0
chemos=chemo_fh.readlines()[1:]
chemo_result=0
recommend_drug=[]
normal_drug=[]
restrict_drug=[]
while bool<len(chemos):
    chemo={}
    lines=chemos[bool].strip().split("\t")
    chemo['bool1']=bool+1
    chemo['name1']=lines[0]
    chemo['result1']=lines[4]
    if lines[3] == '推荐':
#        chemo['result1']=RichText('推荐使用', color='00FF00')
        chemo_result+=1
        recommend_drug.append(chemo['name1'])
    elif lines[3] == '常规':
#        chemo['result1']=RichText('常规使用')
        normal_drug.append(chemo['name1'])
    elif lines[3] == '谨慎':
#        chemo['result1']=RichText('谨慎使用', color='FF0000')
        restrict_drug.append(chemo['name1'])
    if bool+1<len(chemos):
        lines=chemos[bool+1].strip().split("\t")
        chemo['bool2']=bool+2
        chemo['name2']=lines[0]
        chemo['result2']=lines[4]    
        if lines[3] == '推荐':
#            chemo['result2']=RichText('推荐使用', color='00FF00')
            chemo_result+=1
            recommend_drug.append(chemo['name2'])
        elif lines[3] == '常规':
#            chemo['result2']=RichText('常规使用')
            normal_drug.append(chemo['name2'])
        elif lines[3] == '谨慎':
#            chemo['result2']=RichText('谨慎使用', color='FF0000')
            restrict_drug.append(chemo['name2'])
#    print(chemo)
    context['chemo'].append(chemo)
    bool+=2
context['chemo_result']=chemo_result
chemo_detail=[]
chemo_detail_file=''.join([output_dir,'/chemo/',name,".drug.infos.txt"])
chemo_data=pd.read_table(chemo_detail_file,sep="\t")
chemo_drugs=chemo_data['药物'].drop_duplicates()
context['recommend_drug']=','.join(recommend_drug)
context['normal_drug']=','.join(normal_drug)
context['restrict_drug']=','.join(restrict_drug)

for drug in chemo_drugs:
    c={}
    c['drug']=drug
    c['info']=[]
    for index,row in chemo_data[chemo_data['药物'] == drug].iterrows():        
        d={}
        d['gene']=row['检测基因']
        d['site']=row['检测位点']
        d['gt']=row['基因型']
        d['level']=row['证据等级']
        d['sig']=row['用药提示']
        c['info'].append(d)
    chemo_detail.append(c)

context['chemo_detail']=chemo_detail
context['sensitive_resistant_drug']=sensitive_resistant_drug

##化疗联合用药
chemo_comb_file=''.join([output_dir,'/chemo/',name,".chemo.comb.txt"])
chemo=pd.read_table(chemo_comb_file,sep="\t")
type=chemo['癌种'].drop_duplicates()

bool=-1
chemo_comb=[]
for i in type:
    bool+=1
    chemo_comb.append({'type':i,'drug':[]})
    for index,row in chemo[chemo['癌种']==i].iterrows():
        info={}
        info['name']=row['用药方案']
        info['abbr']=row['方案缩写']
        info['sig']=row['临床提示']
        chemo_comb[bool]['drug'].append(info)
context['chemo_comb']=chemo_comb

##hereditary cancer
if os.path.exists(''.join([output_dir,'/hereditary/',name,'.hereditary.pre.txt'])):
    context['hereditary_cancer_1']=[]
    context['hereditary_cancer_2']=[]
    hereditary_file1=''.join([output_dir,'/hereditary/',name,".hereditary.txt"])
    hereditary_file2=''.join([output_dir,'/hereditary/',name,".risk.txt"])
    hereditary_file1_fh=open(hereditary_file1,'r')
    hereditary_file2_fh=open(hereditary_file2,'r')

    hereditary_result=0
    hereditary_result_summary=[]
    hereditary_disease=[]
    if os.path.getsize(hereditary_file1)>0:
        hereditary_file1_fh=open(hereditary_file1,'r')
        for line in hereditary_file1_fh.readlines()[1:]:
            hereditary_cancer_1={}
            lines=line.strip().split("\t")
            hereditary_cancer_1['gene']=lines[0]
            hereditary_cancer_1['syndrome']=lines[1]
            hereditary_cancer_1['hereditary_type']=lines[2]
            hereditary_cancer_1['type']=lines[3]
            hereditary_cancer_1['result']=lines[4]
            hereditary_result+=len(lines[4].split(";"))
            hereditary_result_summary.append(hereditary_cancer_1['gene'] + ' ' + hereditary_cancer_1['result'])
            hereditary_disease.append(hereditary_cancer_1['syndrome'])
            context['hereditary_cancer_1'].append(hereditary_cancer_1)

    context['hereditary_result']=hereditary_result
    if hereditary_result_summary:
        context['hereditary_disease']=';'.join(hereditary_disease)
        context['hereditary_result_summary']=' | '.join(hereditary_result_summary)
    else:
        context['hereditary_disease']='/'
        context['hereditary_result_summary']='未检测到相关基因突变'

    hereditary_risk=[]
    bool=0
    heres=hereditary_file2_fh.readlines()[1:]
    while bool<len(heres):
        hereditary_cancer_2={}
        lines=(heres[bool]).strip().split("\t")
        hereditary_cancer_2['type1']=lines[0]
        if lines[1] == '偏高':
            hereditary_risk.append(lines[0])
            hereditary_cancer_2['risk1']=RichText('偏高', color='FF0000')
        elif lines[1] == '同一般人群':
            hereditary_cancer_2['risk1']=RichText('同一般人群')
        if bool+1<len(heres):
            lines=heres[bool+1].strip().split("\t")
            hereditary_cancer_2['type2']=lines[0]
            if lines[1] == '偏高':
                hereditary_cancer_2['risk2']=RichText('偏高', color='FF0000')
            elif lines[1] == '同一般人群':
                hereditary_cancer_2['risk2']=RichText('同一般人群')
        context['hereditary_cancer_2'].append(hereditary_cancer_2)
        bool+=2

    if hereditary_risk:
        context['hereditary_risk']=','.join(hereditary_risk) + '风险可能较高'
    else:
        context['hereditary_risk']='风险同一般人群' 
    if len(context['hereditary_cancer_1'])==0:
        context['hereditary_cancer_1']=[{'gene':'/','syndrome':'/','hereditary_type':'/','type':'/','result':'/'}]        
    
##可能获益的临床药物处理
total_drug_count=[]
for i in context['list1']:
    if i['drug_A'] != '/':
        for j in i['drug_A'].split("\n"):
            if j not in total_drug_count:
                total_drug_count.append(j)
    if i['drug_B'] != '/':
        for j in i['drug_B'].split("\n"):
            if j not in total_drug_count:
                total_drug_count.append(j)
    if i['drug_C'] != '/':
        for j in i['drug_C'].split("\n"):
            if j not in total_drug_count:
                total_drug_count.append(j)

context['total_drug_count']=len(total_drug_count)                

##去重处理
context['clingenes1']=[]
context['clingenes2']=[]
for i in context['clingene1']:
    if i not in context['clingenes1']:
        context['clingenes1'].append(i)

for i in context['clingene2']:
    if i not in context['clingenes2'] and i not in context['clingenes1']:
        context['clingenes2'].append(i) 

##检测到的基因变异
context['total_mut_count']=len(context['clingenes1'])+len(context['clingenes2'])


##本癌种FDA/NMPA/NCCN批准基因检测
indication_fh=open(indication_file,'r',encoding='utf-8').readlines()
indication_genes=[]
for line in indication_fh[1:]:
    indication={}
    indication['gene']=line.strip().split("\t")[0]
    indication['content']=line.strip().split("\t")[1]
    if indication['gene'] in context['list3'].keys():
        indication['result']=RichText(context['list3'][indication['gene']], color='FF0000')
    else:
        indication['result']='未检出变异'
    context['indication'].append(indication)

##qc处理
qc_file=''.join([output_dir,'/qc/',name,'_qc.txt'])
qc=pd.read_table(qc_file,sep="\t",header=None,index_col=0,names=['A','B'])

Q30=qc.loc['Q30(%)','B']
if Q30>=85:
    Q30_result='合格'
else:
    Q30_result='警戒'

depth=qc.loc['mean_depth(dedup)','B']
if Sample_type == 'c':
    if depth>=1000:
        depth_result='合格'
    else:
        depth_result='警戒'
elif Sample_type == 't':
    if depth>=500:
        depth_result='合格'
    else:
        depth_result='警戒'

uniformity=qc.loc['coverage(>=0.2*meanx)','B']
if uniformity>=90:
    uniformity_result='合格'
else:
    uniformity_result='警戒'

if Q30_result=='合格' and depth_result=='合格' and uniformity_result=='合格':
    context['qc_result']='合格'
else:
    context['qc_result']='警戒'

context['Q30']=Q30
context['Q30_result']=Q30_result
context['depth']=depth
context['uniformity']=uniformity
context['depth_result']=depth_result
context['uniformity_result']=uniformity_result 

     

##阴性模块处理
##list1
if len(context['list1'])==0:
    context['list1']=[{'gene':'/','freq':'/','drug_A':'/','drug_B':'/','drug_C':'/','drug_D':'/'}]

##list2
if len(context['list2'])==0:
    context['list2']= {'/':[{'drug':'/','effect':'/','tumor':'/','evidence':'/','sig':'/'}]}
    context['genefunc']['/']='/'


##clingenes,nonclingenes 
if len(context['clingenes1'])==0:
    context['clingenes1']=[{'gene':'/','transcript':'/','nacid':'/','aacid':'/','exon':'/','muttype':'/','freq':'/'}]
if len(context['clingenes2'])==0:
    context['clingenes2']=[{'gene':'/','transcript':'/','nacid':'/','aacid':'/','exon':'/','muttype':'/','freq':'/'}]
if len(context['nonclingenes'])==0:
    context['nonclingenes']=[{'gene':'/','transcript':'/','nacid':'/','aacid':'/','exon':'/','muttype':'/','freq':'/'}]

##sensitive_resistant_drug
if len(context['sensitive_resistant_drug'][0]['drug'])==0:
    context['sensitive_resistant_drug'][0]['drug']=[{'name':'/','mechanism':'/'}]
if len(context['sensitive_resistant_drug'][1]['drug'])==0:
    context['sensitive_resistant_drug'][1]['drug']=[{'name':'/','mechanism':'/'}]

##mmr
if len(context['mmr'])==0:
    context['mmr']=[{'gene':'/','transcript':'/','nacid':'/','aacid':'/','muttype':'/','freq':'/','sig':'/'}]

##info
post_file=''.join([output_dir,'/qc/',name,'_post.json'])
sex='/'
age='/'
phone='/'
medical_history='/'
family_history='/'
sample_id=name
sample_type='/'
report_date=time.strftime("%Y-%m-%d", time.localtime())
arrival_date=report_date
cancer_type='/'
pathologic_diagnosis='/'

if os.path.isfile(post_file):
# if post_file.exists():
    post_fh=open(post_file,'r')
    post=json.load(post_fh)
    name=post["data"][0]["name"]
    sex=post["data"][0]["gender"]
    age=post["data"][0]["age"]
    medical_history=post["data"][0]["treatHistory"]
    family_history=post["data"][0]["sickFamilyHistory"]
    sample_id=post["data"][0]["barcode"]
    # sample_id_control=post["data"][0]["barcode_N"]
    sample_type=post["data"][0]["source"]
    # sample_type_control=post["data"][0]["source_N"]
#    sample_type_control = post["data"][0].get('source_N', '/')
    arrival_date=post["data"][0]["receiveTime"].split(' ')[0]
    cancer_type=post["data"][0]["zlType"]
    pathologic_diagnosis=post["data"][0]["treatResult"]

context['info']={
'name':name,
'sex':sex,
'age':age,
'phone':phone,
'medical_history':medical_history,
'family_history':family_history,
'sample_id':sample_id,
'sample_type':sample_type,
'report_date':report_date,
'arrival_date':arrival_date,
'cancer_type':cancer_type,
'pathologic_diagnosis':pathologic_diagnosis}
context['report_time']=report_date

##模板替换
file_real = os.path.realpath(sys.argv[0])
Exe_Path = os.path.dirname(file_real)

report_template={'lung85gene':{'t':'lung85-tissue-oem.docx','c':'lung85-blood-oem.docx'},
'crc88gene':{'t':'CRC88-tissue-oem.docx','c':'CRC88-blood-oem.docx'}}
doc_full = os.path.join(Exe_Path, report_template[projcet][Sample_type])

doc = DocxTemplate(doc_full)

doc.render(context)
doc.save(report_file)