ks/utils/format.py

#coding=utf-8

import datetime
import traceback
import tablib
import base64
from datetime import timedelta

from docx import Document
from docx.oxml.ns import qn
from openpyxl.utils.exceptions import InvalidFileException

def strfdate(d):
    if d:
        return d.strftime('%Y-%m-%d')
    else:
        return ''

def strftime(t):
    if t:
        return t.strftime('%Y-%m-%d %H:%M')
    else:
        return ''

def strfsecond(second):
    sec = timedelta(seconds=second)
    d = datetime.datetime(1,1,1) + sec
    if d.hour > 0:
        if d.minute > 0:
            if d.second > 0:
                retval = "%d小时%d分钟%d秒" % (d.hour, d.minute, d.second)
            else:
                retval = "%d小时%d分钟" % (d.hour, d.minute)
        else:
            if d.second > 0:
                retval = "%d小时%d秒" % (d.hour, d.second)
            else:
                retval = "%d小时" % (d.hour)
    else:
        if d.minute > 0:
            if d.second > 0:
                retval = "%d分钟%d秒" % (d.minute, d.second)
            else:
                retval = "%d分钟" % (d.minute)
        else:
            retval = "%d秒" % (d.second)
    return retval


def clean_datetime_range(data, fieldname):
    if data is not None and fieldname in data and data[fieldname] != '':
        t = data[fieldname].split(' - ')
        data = data.copy()
        data[fieldname+'_after'] = t[0]
        data[fieldname+'_before'] = t[1] + ' 23:59:59'
        data.pop(fieldname)
    return data


class ExcelImporter():
    @staticmethod
    def validity(file):
        status = {
            'success': True,
            'errors': '',
            'data': []
        }
        if file == None:
            status['success'] = False
            status['errors'] = u"请上传数据文件"
        else:
            try:
                data = tablib.import_set(file, format='xlsx').dict
                if len(data) == 0:
                    status['success'] = False
                    status['errors'] = u"上传的文件内没有发现数据"
                else:
                    status['data'] = data
            except InvalidFileException:
                status['success'] = False
                status['errors'] = u"请上传<strong>xlsx</strong>格式的数据文件，老版本的xls格式不被支持！"
            except Exception as e:
                traceback.print_exc()
                status['success'] = False
                status['errors'] = u"导入失败"
        return status

class WordImporter():
    @staticmethod
    def parse(file):
        doc = Document(file)
        question_data = []
        question = {}
        is_option = False
        is_image = False

        for para in doc.paragraphs:            
            text = para.text.strip()
            if text:
                if text.startswith("【序号】"):
                    question = {}
                    is_option = False
                    is_image = False
                    question_data.append(question)
                    question['num'] = text.split("【序号】")[-1].strip()

                elif text.startswith("【题文】"):
                    question['title'] = text.split("【题文】")[-1].strip()

                elif text.startswith("【图片】"):
                    is_image = True
                    question['images'] = []

                elif text.startswith("【章节】"):
                    question['chapter'] = text.split("【章节】")[-1].strip()

                elif text.startswith("【题型】"):
                    #print("====>", text)
                    question['type'] = text.split("【题型】")[-1].strip()

                elif text.startswith("【答案】"):
                    print("====>", text)
                    question['answer'] = text.split("【答案】")[-1].strip()

                elif text.startswith("【解析】"):
                    question['analysis'] = text.split("【解析】")[-1].strip()

                elif text.startswith("【难度】"):
                    question['difficulty'] = text.split("【难度】")[-1].strip()
                    
                elif text.startswith("【分数】"):
                    question['score'] = text.split("【分数】")[-1].strip()

                elif text.startswith("【选项】"):
                    is_option = True
                    question['options'] = []
                
                elif is_option and text:
                    question['options'].append(text)

            elif len(para.runs) > 0 and is_image:
                image_data = WordImporter.extract_image(para)
                image_data = base64.b64encode(image_data).decode('utf-8')
                question['images'].append(image_data)

        #print(question_data)
        return question_data

    @staticmethod
    def extract_image(para):
        for run in para.runs:
            if run.element.xpath('.//a:blip'):
                blip = run.element.xpath('.//a:blip')[0]
                embed = blip.get(qn('r:embed'))
                related_part = run.part.related_parts[embed]
                image_bytes = related_part.blob
                return image_bytes
        return None