add:log

冯轩
Showing 3 changed files with 26 additions and 4 deletions
src-0424.zip
src/apps/doc/management/commands/ocr_process.py
src/apps/doc/ocr/wb.py
--- a/src-0424.zip 0 → 100644
View file @cd509dc
+++ b/src-0424.zip 0 → 100644
View file @cd509dc
--- a/src/apps/doc/management/commands/ocr_process.py
View file @cd509dc
+++ b/src/apps/doc/management/commands/ocr_process.py
View file @cd509dc
@@ -178,6 +178,8 @@ class Command(BaseCommand, LoggerMixin):
    #     self.online_log.info('{0} [edms download success] [pdf_path={1}]'.format(self.log_base, pdf_path))
    def bs_process(self, wb, ocr_data, bs_summary, unknown_summary, classify, res_list, pno, ino, part_idx, income_keywords_dictionary):
+        self.online_log.warn('{0} [bs_process] [ocr_data={1}] [bs_summary={2}] [unknown_summary={3}] [classify={4}] [res_list={5}] [pno={6}] [ino={7}] [part_idx={8}] [income_keywords_dictionary={9}]'.format(
+            self.log_base, ocr_data, bs_summary, unknown_summary, classify, res_list, pno, ino, part_idx, income_keywords_dictionary))
        sheets = ocr_data.get('data', [])
        if not sheets:
            res_list.append((pno, ino, part_idx, consts.RES_SUCCESS_EMPTY))
@@ -2053,8 +2055,8 @@ class Command(BaseCommand, LoggerMixin):
                        try:
                            # 重构Excel文件
-                            # src_excel_path = os.path.join(doc_data_path, 'src.xlsx')
+                            src_excel_path = os.path.join(doc_data_path, 'src.xlsx')
-                            # wb.save(src_excel_path)
+                            wb.save(src_excel_path)
                            #need_follow表示在上传edms时文件名是否要添加"关注"两字
                            count_list, need_follow = wb.rebuild(merged_bs_summary, license_summary, res_list, doc.document_scheme, contract_result, doc.metadata, financial_statement_dict, financial_explanation_dict, down_payment_dict)
                            wb.save(excel_path)
--- a/src/apps/doc/ocr/wb.py
View file @cd509dc
+++ b/src/apps/doc/ocr/wb.py
View file @cd509dc
@@ -122,13 +122,19 @@ class BSWorkbook(Workbook, LoggerMixin):
        header_col_list = []
        for first_row in ws.iter_rows(max_row=1, min_row=1, values_only=True):
            sheet_header_info.setdefault(ws.title, {}).setdefault(consts.HEADER_KEY, first_row)
+            self.online_log.warn('{0} [header_collect_1] [first_row={1}] [sheet_header_info={2}]'.format(
+                    self.log_base, first_row, sheet_header_info))
            for idx, header_value in enumerate(first_row):
                header_col = self.get_header_col(header_value, classify)
+                self.online_log.warn('{0} [header_collect_2] [idx={1}] [header_value={2}] [header_col={3}]'.format(
+                    self.log_base, idx, header_value, header_col))
                if classify == consts.MS_CLASSIFY and header_col == consts.OVER_KEY and \
                        header_value == '账户余额现转标志' and not first_row[idx - 1]:
                    idx -= 1
                if header_col is not None:
                    header_col_list.append((idx, header_col))
+        self.online_log.warn('{0} [header_collect_3] [header_col_list={1}]'.format(
+                    self.log_base, header_col_list))
        find_count = len(header_col_list)
        if find_count < 2:
@@ -136,15 +142,25 @@ class BSWorkbook(Workbook, LoggerMixin):
        else:
             for idx, header_col in header_col_list:
                sheet_header_info.setdefault(ws.title, {}).setdefault(header_col, idx)
+                self.online_log.warn('{0} [header_collect_4] [sheet_header_info={1}]'.format(
+                    self.log_base, sheet_header_info))
                find_col_set = sheet_header_info.setdefault(ws.title, {}).setdefault(consts.FIND_COL_KEY, set())
                find_col_set.add(idx)
+                self.online_log.warn('{0} [header_collect_5] [sheet_header_info={1}]'.format(
+                    self.log_base, sheet_header_info))
                col_count = header_info.setdefault(header_col, {}).get(idx)
                header_info.setdefault(header_col, {})[idx] = 1 if col_count is None else col_count+1
+                self.online_log.warn('{0} [header_collect_6] [header_info={1}]'.format(
+                    self.log_base, header_info))
        sheet_header_info.setdefault(ws.title, {}).setdefault(consts.FIND_COUNT_KEY, find_count)
+        self.online_log.warn('{0} [header_collect_7] [sheet_header_info={1}]'.format(
+                    self.log_base, sheet_header_info))
        min_row = 1 if find_count == 0 else 2
        sheet_header_info.setdefault(ws.title, {}).setdefault(consts.MIN_ROW_KEY, min_row)
        max_column_list.append(ws.max_column)
+        self.online_log.warn('{0} [header_collect_8] [sheet_header_info={1}] [header_info={2}] [max_column_list={3}]'.format(
+                    self.log_base, sheet_header_info, header_info, max_column_list))
    @staticmethod
    def header_statistics(sheet_header_info, header_info, classify, special_nhzs):
@@ -194,7 +210,7 @@ class BSWorkbook(Workbook, LoggerMixin):
        return statistics_header_info, max_find_count
    @staticmethod
-    def get_data_col_min_row(sheet, sheet_header_info, header_info, classify):
+    def get_data_col_min_row(self, sheet, sheet_header_info, header_info, classify):
        date_col = sheet_header_info.get(sheet, {}).get(consts.DATE_KEY)
        if date_col is None:
            date_col_dict = header_info.get(consts.DATE_KEY, {})
@@ -273,6 +289,8 @@ class BSWorkbook(Workbook, LoggerMixin):
        return reverse_trend
    def sheet_split(self, ws, date_col, min_row, month_mapping, reverse_trend_list, date_list, date_statistics):
+        self.online_log.warn('{0} [sheet_split] [date_col={1}] [min_row={2}] [month_mapping={3}] [reverse_trend_list={4}] [date_list={5}] [date_statistics={6}]'.format(
+                    self.log_base, date_col, min_row, month_mapping, reverse_trend_list, date_list, date_statistics))
        if date_col is None:
            # month_info process
            month_info = month_mapping.setdefault('xxxx-xx', [])
@@ -749,7 +767,9 @@ class BSWorkbook(Workbook, LoggerMixin):
            reverse_trend_list = []  # 用于判断倒序与正序
            for sheet in sheets_list:
                ws = self.get_sheet_by_name(sheet)
-                date_col, min_row = self.get_data_col_min_row(sheet, sheet_header_info, header_info, classify)
+                date_col, min_row = self.get_data_col_min_row(self, sheet, sheet_header_info, header_info, classify)
+                self.online_log.warn('{0} [bs_rebuild] [date_col={1}] [min_row={2}]'.format(
+                    self.log_base, date_col, min_row))
                self.sheet_split(ws, date_col, min_row, month_mapping, reverse_trend_list, date_list, date_statistics)
            if date_statistics is True and len(date_list) > 1: