def classified(self):
"""
设计国土行业数据guoqing_frame的验证规则（国情影像—分幅影像）
完成 负责人 王学谦 在这里检验guoqing_frame的识别规则
:return:
"""
super().classified()
file_main_name = self.file_info.file_main_name
file_ext = self.file_info.file_ext # 初始化需要的参数
file_path = self.file_info.file_path
file_object_name = file_main_name[:]
if len(file_main_name) >= 21: # 本类文件默认至少为20位
file_object_name = file_main_name[:20] # 截取前20位
elif len(file_main_name) == 20: # 20位基本为附属文件
pass
else:
return self.Object_Confirm_IUnKnown, self._object_name
match_str = '(?i)^' + file_object_name + r'[a-zA-Z][.]tif'
check_file_main_name_exist = \
CFile.find_file_or_subpath_of_path(file_path, match_str, CFile.MatchType_Regex)
if not check_file_main_name_exist: # 检查主文件存在性
return self.Object_Confirm_IUnKnown, self._object_name
# 文件名第1，4，11，12，16，21位为字母，第2，3，5-10，14，15，17-20位是数字
name_sub_1 = file_main_name[0:1]
name_sub_2_to_3 = file_main_name[1:3]
name_sub_4 = file_main_name[3:4]
name_sub_5_to_10 = file_main_name[4:10]
name_sub_11_to_12 = file_main_name[10:12]
name_sub_14_to_15 = file_main_name[13:15]
name_sub_16 = file_main_name[15:16]
name_sub_17_to_20 = file_main_name[16:20]
name_sub_21 = file_main_name[20:21]
if CUtils.text_is_alpha(name_sub_1) is False \
or CUtils.text_is_numeric(name_sub_2_to_3) is False \
or CUtils.text_is_alpha(name_sub_4) is False \
or CUtils.text_is_numeric(name_sub_5_to_10) is False \
or CUtils.text_is_alpha(name_sub_11_to_12) is False \
or CUtils.text_is_numeric(name_sub_14_to_15) is False \
or CUtils.text_is_alpha(name_sub_16) is False \
or CUtils.text_is_numeric(name_sub_17_to_20) is False \
or CUtils.text_is_alpha(name_sub_21) is False:
return self.Object_Confirm_IUnKnown, self._object_name
if len(file_main_name) == 21 and CUtils.equal_ignore_case(
file_ext, 'tif'):
self._object_confirm = self.Object_Confirm_IKnown
self._object_name = file_main_name
self.add_file_to_detail_list(file_object_name) # 在这里设置不同名的附属文件
else:
self._object_confirm = self.Object_Confirm_IKnown_Not
self._object_name = None
return self._object_confirm, self._object_name
def classified(self):
self._object_confirm = self.Object_Confirm_IUnKnown
self._object_name = None
current_path = self.file_info.file_name_with_full_path
if (self.file_info.file_name_without_path.lower().endswith('.gdb')) \
and CFile.find_file_or_subpath_of_path(current_path, '*.gdbtable'):
self._object_confirm = self.Object_Confirm_IKnown
self._object_name = self.file_info.file_main_name
return self._object_confirm, self._object_name
def classified(self):
"""
设计国土行业数据guoqing_scene_noblock的验证规则（国情影像—非分块）,不带数字
完成 负责人 王学谦 在这里检验guoqing_scene_noblock的识别规则
:return:
"""
super().classified()
file_main_name = self.file_info.file_main_name
file_ext = self.file_info.file_ext # 初始化需要的参数
file_path = self.file_info.file_path
file_object_name = file_main_name[:] # 这里需要取得规则匹配用的‘对象名’，即去除尾部字母等字符的名
# 正则表达式，(?i)代表大小写不敏感，^代表字符串开头，$代表字符串结尾
# [a-z]指匹配所有小写字母，配合(?i)匹配所有字母，{2}代表前面的匹配模式匹配2次，即[a-z]{2}匹配两个字母
# \d匹配数字，即[0-9]，即\d+匹配一个或多个非空字符，\d{4}匹配四个任意数字
# [0123]一般指匹配一个括号中任意字符，即匹配0到3
# \S用于匹配所有非空字符，+代表匹配前面字符的数量为至少一个，即\S+匹配一个或多个非空字符
if len(file_main_name) < 13:
return self.Object_Confirm_IUnKnown, self._object_name
# 下面正则：开头两个字母，字母后任意数量字符,而后匹配8位时间，4位任意数字（年份），[01]\d为月份，[0123]\d日
if CUtils.text_match_re(
file_main_name, r'(?i)^[a-z]{2}\S+'
r'\d{4}[01]\d[0123]\d[a-z]$'): # 结尾为单个字母的情况
file_object_name = file_main_name[:-1] # 这里需要取得规则匹配用的‘对象名’，即去除尾部字母
elif CUtils.text_match_re(
file_main_name,
r'(?i)^[a-z]{2}\S+' # 带-的抛出
r'\d{4}[01]\d[0123]\d[a-z][-]\d+$'):
return self.Object_Confirm_IUnKnown, self._object_name
elif CUtils.text_match_re(
file_main_name,
r'(?i)^[a-z]{2}\S+' # 尾部没字母取原本主名
r'\d{4}[01]\d[0123]\d$'):
pass
elif CUtils.text_match_re(
file_main_name, r'(?i)^[a-z]{2}\S+'
r'\d{4}[01]\d[0123]\d\S+$'): # 结尾为多个的字符情况
file_object_name_list = re.findall(
r'(?i)^([a-z]{2}\S+\d{4}[01]\d[0123]\d)\S+$', file_main_name)
file_object_name = file_object_name_list[0] # 剔除结尾多个字符
match_str = '(?i)^' + file_object_name + r'[FMP].img$' # 匹配主文件的规则，即对象名+F/M/P
check_file_main_name_exist = CFile.find_file_or_subpath_of_path(
file_path, match_str, CFile.MatchType_Regex)
if not check_file_main_name_exist: # 检查主文件存在性
return self.Object_Confirm_IUnKnown, self._object_name
"""文件名第1-2位为字母，最后1位是字母在F/P/M中，倒数2-9位是数字"""
name_sub_1_to_2 = file_object_name[0:2]
name_sub_backwards_9_to_2 = file_object_name[-8:]
if CUtils.text_is_alpha(name_sub_1_to_2) is False \
or CUtils.text_is_numeric(name_sub_backwards_9_to_2) is False:
return self.Object_Confirm_IUnKnown, self._object_name
# 作为对象的主文件存在优先级，F-M-P,比如需要F的文件不存在，M才能是主文件
# 能跑到这里的文件已经可以认为不是主文件，就是附属文件
match_str_f = '(?i)^' + file_object_name + r'[F].img$'
match_str_fm = '(?i)^' + file_object_name + r'[FM].img$'
name_sub_backwards_1 = file_main_name[-1:]
if CUtils.equal_ignore_case(name_sub_backwards_1.lower(), 'f') \
and CUtils.equal_ignore_case(file_ext.lower(), 'img'):
self._object_confirm = self.Object_Confirm_IKnown
self._object_name = file_main_name
self.add_file_to_detail_list(file_object_name)
elif CUtils.equal_ignore_case(name_sub_backwards_1.lower(), 'm') \
and CUtils.equal_ignore_case(file_ext.lower(), 'img') \
and not CFile.find_file_or_subpath_of_path(file_path, match_str_f, CFile.MatchType_Regex):
self._object_confirm = self.Object_Confirm_IKnown
self._object_name = file_main_name
self.add_file_to_detail_list(file_object_name)
elif CUtils.equal_ignore_case(name_sub_backwards_1.lower(), 'p') \
and CUtils.equal_ignore_case(file_ext.lower(), 'img') \
and not CFile.find_file_or_subpath_of_path(file_path, match_str_fm, CFile.MatchType_Regex):
self._object_confirm = self.Object_Confirm_IKnown
self._object_name = file_main_name
self.add_file_to_detail_list(file_object_name)
else:
self._object_confirm = self.Object_Confirm_IKnown_Not
self._object_name = None
return self._object_confirm, self._object_name
def classified(self):
"""
关键字识别
"""
super().classified()
# 预获取需要的参数
file_path = self.file_info.file_path
file_main_name = self.file_info.file_main_name
file_ext = self.file_info.file_ext
# 预定义逻辑参数 数据文件匹配
object_file_name_flag = False
object_file_path_flag = False
object_file_ext_flag = False
object_affiliated_file_main_flag = False
object_file_affiliated_flag = False
object_keyword_list = self.get_classified_character_of_object_keyword()
if len(object_keyword_list) > 0:
for keyword_info in object_keyword_list:
keyword_id = CUtils.dict_value_by_name(keyword_info,
self.Name_ID, None)
regex_match = CUtils.dict_value_by_name(
keyword_info, self.Name_RegularExpression, '.*')
if regex_match is None:
regex_match = '.*'
if CUtils.equal_ignore_case(keyword_id, self.Name_FileName):
if CUtils.text_match_re(file_main_name, regex_match):
object_file_name_flag = True
elif CUtils.equal_ignore_case(keyword_id, self.Name_FilePath):
if CUtils.text_match_re(file_path, regex_match):
object_file_path_flag = True
elif CUtils.equal_ignore_case(keyword_id, self.Name_FileExt):
if CUtils.text_match_re(file_ext, regex_match):
object_file_ext_flag = True
else:
same_name_file_list = CFile.file_or_dir_fullname_of_path(
file_path, False,
'(?i)^' + file_main_name + '[.].*$',
CFile.MatchType_Regex)
if len(same_name_file_list) > 0:
for same_name_file in same_name_file_list:
same_name_file_ext = CFile.file_ext(
same_name_file)
if CUtils.text_match_re(
same_name_file_ext, regex_match):
object_affiliated_file_main_flag = True
elif CUtils.equal_ignore_case(keyword_id,
self.Name_FileAffiliated):
affiliated_file_path = CUtils.dict_value_by_name(
keyword_info, self.Name_FilePath, None)
if affiliated_file_path is not None:
if CFile.find_file_or_subpath_of_path(
affiliated_file_path, regex_match,
CFile.MatchType_Regex):
object_file_affiliated_flag = True
else:
object_file_affiliated_flag = True
# 预定义逻辑参数 附属文件匹配
affiliated_file_name_flag = False
affiliated_file_path_flag = False
affiliated_file_ext_flag = False
affiliated_file_main_flag = False
affiliated_keyword_list = self.get_classified_character_of_affiliated_keyword(
)
if len(affiliated_keyword_list) > 0:
for keyword_info in affiliated_keyword_list:
keyword_id = CUtils.dict_value_by_name(keyword_info,
self.Name_ID, None)
regex_match = CUtils.dict_value_by_name(
keyword_info, self.Name_RegularExpression, '.*')
if regex_match is None:
regex_match = '.*'
if CUtils.equal_ignore_case(keyword_id, self.Name_FileName):
if CUtils.text_match_re(file_main_name, regex_match):
affiliated_file_name_flag = True
elif CUtils.equal_ignore_case(keyword_id, self.Name_FilePath):
if CUtils.text_match_re(file_path, regex_match):
affiliated_file_path_flag = True
elif CUtils.equal_ignore_case(keyword_id, self.Name_FileExt):
if CUtils.text_match_re(file_ext, regex_match):
affiliated_file_ext_flag = True
elif CUtils.equal_ignore_case(keyword_id, self.Name_FileMain):
affiliated_file_path = CUtils.dict_value_by_name(
keyword_info, self.Name_FilePath, None)
if affiliated_file_path is not None:
if CFile.find_file_or_subpath_of_path(
affiliated_file_path, regex_match,
CFile.MatchType_Regex):
affiliated_file_main_flag = True
if object_file_name_flag and object_file_path_flag and \
object_file_ext_flag and object_file_affiliated_flag:
self._object_confirm = self.Object_Confirm_IKnown
self._object_name = file_main_name
self.set_custom_affiliated_file()
elif affiliated_file_name_flag and affiliated_file_path_flag and \
affiliated_file_ext_flag and affiliated_file_main_flag:
self._object_confirm = self.Object_Confirm_IKnown_Not
self._object_name = None
elif object_file_name_flag and object_file_path_flag and object_affiliated_file_main_flag:
self._object_confirm = self.Object_Confirm_IKnown_Not
self._object_name = None
else:
self._object_confirm = self.Object_Confirm_IUnKnown
self._object_name = None
return self._object_confirm, self._object_name
def classified(self):
"""
设计国土行业数据third_survey_noblock的验证规则（三调影像—非分块）
完成 负责人 王学谦 在这里检验third_survey_noblock的识别规则
:return:
"""
super().classified()
file_main_name = self.file_info.file_main_name
file_ext = self.file_info.file_ext # 初始化需要的参数
file_path = self.file_info.file_path
if len(file_main_name) > 6:
file_name_before_six = file_main_name[0:6] # 截取前六位行政区划代码
else:
return self.Object_Confirm_IUnKnown, self._object_name # 主名必然大于6
if not CUtils.text_is_numeric(CUtils.any_2_str(file_name_before_six)):
return self.Object_Confirm_IUnKnown, self._object_name # 前六位必然为数字
# 正则表达式，(?i)代表大小写不敏感，^代表字符串开头，$代表字符串结尾
# \S用于匹配所有非空字符，+代表匹配前面字符的数量为至少一个，即\S+匹配一个或多个非空字符
# \d匹配数字，即[0-9]，即\d+匹配一个或多个非空字符
match_str = '(?i)^' + file_name_before_six + r'\S+dom.img$'
check_file_main_name_exist = CFile.find_file_or_subpath_of_path(
file_path, match_str, CFile.MatchType_Regex)
if not check_file_main_name_exist: # 检查主文件存在性
return self.Object_Confirm_IUnKnown, self._object_name
# file_name_before_six_name = ''
# file_metadata_name = '{0}{1}'.format(file_name_before_six, file_name_before_six_name)
# file_metadata_name_with_path = CFile.join_file(file_path, file_metadata_name)
# check_file_mdb_exist = CFile.file_or_path_exist('{0}.mdb'.format(file_metadata_name_with_path))
# if not check_file_mdb_exist: # 检查mdb文件存在性
# return self.Object_Confirm_IUnKnown, self._object_name
if len(file_main_name) >= 12:
name_sub_7_to_8 = file_main_name[6:8]
name_sub_backwards_3_to_1 = file_main_name[-3:]
if CUtils.text_is_alpha(name_sub_7_to_8) \
and CUtils.equal_ignore_case(CUtils.any_2_str(name_sub_backwards_3_to_1).lower(),
'dom'):
if CUtils.equal_ignore_case(file_ext, 'img'):
self._object_confirm = self.Object_Confirm_IKnown
self._object_name = file_main_name
self.add_file_to_detail_list(file_name_before_six)
else:
self._object_confirm = self.Object_Confirm_IKnown_Not
self._object_name = None
else:
# 运行到此的文件，如果格式为以下，则默认为附属文件
affiliated_ext_list = [
'mdb', 'shp', 'shx', 'dbf', 'sbx', 'prj', 'sbn'
]
if file_ext.lower() in affiliated_ext_list:
self._object_confirm = self.Object_Confirm_IKnown_Not
self._object_name = None
else:
return self.Object_Confirm_IUnKnown, self._object_name
else:
# 运行到此的文件，如果格式为以下，则默认为附属文件
affiliated_ext_list = [
'mdb', 'shp', 'shx', 'dbf', 'sbx', 'prj', 'sbn'
]
if file_ext.lower() in affiliated_ext_list:
self._object_confirm = self.Object_Confirm_IKnown_Not
self._object_name = None
else:
return self.Object_Confirm_IUnKnown, self._object_name
return self._object_confirm, self._object_name
def classified(self):
"""
设计国土行业数据guoqing_scene_block的验证规则（国情影像—分块）,带数字 F-1/F-2
完成 负责人 王学谦 在这里检验guoqing_scene_block的识别规则
:return:
"""
super().classified()
file_main_name = self.file_info.file_main_name
file_ext = self.file_info.file_ext # 初始化需要的参数
file_path = self.file_info.file_path
file_object_name = file_main_name[:] # 这里需要取得规则匹配用的‘对象名’，即去除尾部字母等字符的名
# 正则表达式，(?i)代表大小写不敏感，^代表字符串开头，$代表字符串结尾
# [a-z]指匹配所有小写字母，配合(?i)匹配所有字母，{2}代表前面的匹配模式匹配2次，即[a-z]{2}匹配两个字母
# \d匹配数字，即[0-9]，即\d+匹配一个或多个非空字符，\d{4}匹配四个任意数字
# [0123]一般指匹配一个括号中任意字符，即匹配0到3
# \S用于匹配所有非空字符，+代表匹配前面字符的数量为至少一个，即\S+匹配一个或多个非空字符
if len(file_main_name) < 13:
return self.Object_Confirm_IUnKnown, self._object_name
if CUtils.text_match_re(file_main_name, r'(?i)^[a-z]{2}\S+'
r'\d{4}[01]\d[0123]\d[a-z][-]\d+$'): # [a-z][-]\d+$结尾为字母-数字
# re.findall获取在正则表达式中所加括号，括号中的字符，这里去剔除结尾字母-数字后的字符
file_object_name_list = re.findall(r'(?i)^([a-z]{2}\S+\d{4}[01]\d[0123]\d)[a-z][-]\d+$',
file_main_name)
file_object_name = file_object_name_list[0]
elif CUtils.text_match_re(file_main_name, r'(?i)^[a-z]{2}\S+' # 尾部只有单个字母的情况
r'\d{4}[01]\d[0123]\d[FMP]$') and \
CUtils.equal_ignore_case(file_ext.lower(), 'img'):
return self.Object_Confirm_IUnKnown, self._object_name
elif CUtils.text_match_re(file_main_name, r'(?i)^[a-z]{2}\S+' # 尾部只有单个字母的情况
r'\d{4}[01]\d[0123]\d[a-z]$'):
file_object_name = file_main_name[:-1]
# 下面正则：开头两个字母，字母后任意数量字符,而后匹配8位时间，4位任意数字（年份），[01]\d为月份，[0123]\d日
elif CUtils.text_match_re(file_main_name, r'(?i)^[a-z]{2}\S+' # 尾部没字母取原本主名
r'\d{4}[01]\d[0123]\d$'):
pass
elif CUtils.text_match_re(file_main_name, r'(?i)^[a-z]{2}\S+' # 尾部无字母，但是有任意附加字符的情况
r'\d{4}[01]\d[0123]\d\S+$'):
file_object_name_list = re.findall(r'(?i)^([a-z]{2}\S+\d{4}[01]\d[0123]\d)\S+$',
file_main_name)
file_object_name = file_object_name_list[0]
match_str = '(?i)^' + file_object_name + r'[FMP][-]\d+.img$'
check_file_main_name_exist = \
CFile.find_file_or_subpath_of_path(file_path, match_str, CFile.MatchType_Regex)
if not check_file_main_name_exist: # 检查主文件存在性
return self.Object_Confirm_IUnKnown, self._object_name
"""文件名第1-2位为字母，倒数1-3位是在F-1/P-1/M-1中，倒数4-11位是数字"""
name_sub_1_to_2 = file_object_name[0:2]
name_sub_backwards_11_to_4 = file_object_name[-8:]
if CUtils.text_is_alpha(name_sub_1_to_2) is False \
or CUtils.text_is_numeric(name_sub_backwards_11_to_4) is False:
return self.Object_Confirm_IUnKnown, self._object_name
# 取得尾部的字母
name_sub_backwards_fmp_list = re.findall(r'(?i)^[a-z]{2}\S+\d{4}[01]\d[0123]\d([a-z])[-]\d+$',
file_main_name)
# 取得尾部的数字
name_sub_backwards_num_list = re.findall(r'(?i)^[a-z]{2}\S+\d{4}[01]\d[0123]\d[a-z][-](\d+)$',
file_main_name)
# 如果尾部没有数字与字母，但是已经通过前面的过滤，则默认为附属文件
if len(name_sub_backwards_fmp_list) > 0 and len(name_sub_backwards_num_list) > 0:
name_sub_backwards_fmp = name_sub_backwards_fmp_list[0]
name_sub_backwards_num = name_sub_backwards_num_list[0]
match_str_f = '(?i)^' + file_object_name + r'[F][-][' + name_sub_backwards_num + '].img$'
match_str_fm = '(?i)^' + file_object_name + r'[FM][-][' + name_sub_backwards_num + '].img$'
# 作为对象的主文件存在优先级，F-M-P,比如需要F的文件不存在，M才能是主文件
if CUtils.equal_ignore_case(name_sub_backwards_fmp.lower(), 'f') \
and CUtils.equal_ignore_case(file_ext.lower(), 'img'):
self._object_confirm = self.Object_Confirm_IKnown
self._object_name = file_main_name
self.add_file_to_detail_list(file_object_name, name_sub_backwards_num)
elif CUtils.equal_ignore_case(name_sub_backwards_fmp.lower(), 'm') \
and CUtils.equal_ignore_case(file_ext.lower(), 'img') \
and not CFile.find_file_or_subpath_of_path(file_path, match_str_f, CFile.MatchType_Regex):
self._object_confirm = self.Object_Confirm_IKnown
self._object_name = file_main_name
self.add_file_to_detail_list(file_object_name, name_sub_backwards_num)
elif CUtils.equal_ignore_case(name_sub_backwards_fmp.lower(), 'p') \
and CUtils.equal_ignore_case(file_ext.lower(), 'img') \
and not CFile.find_file_or_subpath_of_path(file_path, match_str_fm, CFile.MatchType_Regex):
self._object_confirm = self.Object_Confirm_IKnown
self._object_name = file_main_name
self.add_file_to_detail_list(file_object_name, name_sub_backwards_num)
else:
self._object_confirm = self.Object_Confirm_IKnown_Not
self._object_name = None
else:
self._object_confirm = self.Object_Confirm_IKnown_Not
self._object_name = None
return self._object_confirm, self._object_name
