def gen_table_gt(dir_path, pdf_img_save_dir, table_img_save_dir):
# 将pdf转换为图片，并且截取其中的表格 获得gt信息
table_img_list = []
for cur_dir, next_dir, file_names in os.walk(dir_path):
for file_name in file_names:
name, ext = os.path.splitext(file_name)
if ext != '.pdf': continue
pdf_path = os.path.join(cur_dir, file_name)
print('process {}'.format(pdf_path))
cur_save_dir = os.path.join(pdf_img_save_dir, name)
os.makedirs(cur_save_dir, exist_ok=True)
reg_xml_path = os.path.join(cur_dir, name + '-reg.xml')
str_xml_path = os.path.join(cur_dir, name + '-str.xml')
# 将 pdf 转换为图片
images_path_list = ICDAR2013(pdf_path=pdf_path, save_dir=cur_save_dir).gen_img()
# 提取 xml gt 中的信息
xml_result = ReadXml(reg_xml_path=reg_xml_path, str_xml_path=str_xml_path).get_result()
for dict_res in xml_result:
image_path = images_path_list[dict_res['page']]
img_path, img_gt = extract_table(image_path, dict_res, table_img_save_dir)
table_img_list.append(img_path)
import os
import sys
import time
import xml.dom.minidom
from google_translate import TranslateGoogle
from read_xml import ReadXml
from utils import init_logging
if __name__ == '__main__':
init_logging()
logging.getLogger().level = logging.INFO
# f = codecs.open("translate_file.txt", "w+", 'utf-8')
if len(sys.argv) > 1:
string_list = ReadXml().read_xml(sys.argv[1])
else:
raise Exception("You must add a xml path!")
trans = TranslateGoogle()
with open('lang_map.json', 'r', encoding='utf8')as fp:
languages = json.load(fp)
# print("lang_map.json: {}".format(languages))
# languages.update({'one': 2, 'two': 2})
# logging.info(languages)
for lang, documentName in languages.items():
doc = xml.dom.minidom.Document()
root = doc.createElement('resources')
root.setAttribute('xmlns:android',
"http://schemas.android.com/apk/res/android")
root.setAttribute('xmlns:xliff',
"urn:oasis:names:tc:xliff:document:1.2")
def init_value(self):
read_path = os.path.join(os.path.dirname(os.path.realpath(__file__)),
"xml")
self.read_xml = ReadXml(read_path)
self.model_dict = {}
# init brand EN list.
self.brand_dict = {
"intel": _("intel"),
"zte": _("zte"),
"hasee": _("hasee"),
"apple": _("apple"),
"nokia": _("nokia"),
"alcatel": _("alcatel"),
"google": _("google"),
"asus": _("asus"),
"hp": _("hp"),
"sony": _("sony"),
"hedy": _("hedy"),
"archos": _("archos"),
"boway": _("boway"),
"bird": _("bird"),
"vivo": _("vivo"),
"great wall": _("great wall"),
"changhong": _("changhong"),
"skyworth": _("skyworth"),
"dell": _("dell"),
"philips": _("philips"),
"toshiba": _("toshiba"),
"amazon": _("amazon"),
"sdo": _("sdo"),
"disney": _("disney"),
"haier": _("haier"),
"fujitsu": _("fujitsu"),
"acer": _("acer"),
"lenovo": _("lenovo"),
"gigabyte": _("gigabyte"),
"xiaomi": _("xiaomi"),
"huawei": _("huawei"),
"blackberry": _("blackberry"),
"motorola": _("motorola"),
"sangsung": _("sangsung"),
"meizu ": _("meizu "),
"benq": _("benq"),
"panasonic": _("panasonic"),
"sony ericsson": _("sony ericsson"),
"pioneer": _("pioneer"),
"hyundai": _("hyundai"),
"newman": _("newman"),
"coolpad": _("coolpad"),
"malata": _("malata"),
"malata": _("malata"),
"sharp": _("sharp"),
"gionee": _("gionee"),
"k-touch": _("k-touch"),
"Pantech": _("Pantech"),
"hisense": _("hisense"),
"teclast": _("teclast"),
"cube": _("cube"),
"amoi": _("amoi"),
"doov": _("doov"),
"minte": _("minte"),
"dopod": _("dopod"),
"eton": _("eton"),
"cherr": _("cherr"),
"gaoxinqi": _("gaoxinqi"),
"konka": _("konka"),
"viewsonic": _("viewsonic"),
"xibo": _("xibo"),
"hosin": _("hosin"),
"apanda": _("apanda"),
"iocean": _("iocean"),
"mastone": _("mastone")
}
