fix bug

周伟奇
Showing 3 changed files with 15 additions and 7 deletions
.gitignore
src/apps/doc/mixins.py
src/apps/doc/ocr/wb.py
--- a/.gitignore
View file @266f273
+++ b/.gitignore
View file @266f273
@@ -34,4 +34,5 @@ data/*
 src/*.sh
 test*
-ocr_test.py
\ No newline at end of file
+ocr_test.py
+ocr_process.py
\ No newline at end of file
--- a/src/apps/doc/mixins.py
View file @266f273
+++ b/src/apps/doc/mixins.py
View file @266f273
@@ -18,7 +18,7 @@ class DocHandler:
    def get_doc_list(self, doc_queryset, business_type):
        for doc_dict in doc_queryset:
-            if doc_dict['status'] != DocStatus.COMPLETE.value:
+            if doc_dict['status'] not in [DocStatus.COMPLETE.value, DocStatus.UPLOAD_FAILED.value]:
                continue
            doc_id = doc_dict.get('id')
            doc_dict['pdf_link'] = self.get_link(doc_id, business_type)
--- a/src/apps/doc/ocr/wb.py
View file @266f273
+++ b/src/apps/doc/ocr/wb.py
View file @266f273
@@ -30,7 +30,7 @@ class BSWorkbook(Workbook):
        self.MAX_MEAN = 31
    @staticmethod
-    def header_collect(ws, sheet_header_info, header_info):
+    def header_collect(ws, sheet_header_info, header_info, max_column_list):
        # sheet_header_info = {
        #     'sheet_name': {
        #         'summary_col': 1,
@@ -77,6 +77,7 @@ class BSWorkbook(Workbook):
        sheet_header_info.setdefault(ws.title, {}).setdefault(consts.FIND_COUNT_KEY, find_count)
        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)
    @staticmethod
    def header_statistics(sheet_header_info, header_info, classify):
@@ -135,7 +136,7 @@ class BSWorkbook(Workbook):
            else:
                fixed_col = consts.CLASSIFY_LIST[classify][1][consts.CLASSIFY_MAP[consts.DATE_KEY]]
                if fixed_col not in find_col_set and isinstance(fixed_col, int):
-                    date_col = fixed_col
+                    date_col = fixed_col - 1
        min_row = sheet_header_info.get(sheet, {}).get(consts.MIN_ROW_KEY, 2)
        return date_col, min_row
@@ -283,7 +284,7 @@ class BSWorkbook(Workbook):
                res_str = '{0}.{1}'.format(res_str[:period_idx], res_str[period_idx + 1:])
        return res_str
-    def build_month_sheet(self, ms, card, month_mapping, is_reverse, statistics_header_info):
+    def build_month_sheet(self, ms, card, month_mapping, is_reverse, statistics_header_info, max_column):
        summary_cell_idx = statistics_header_info.get(consts.SUMMARY_KEY)
        date_cell_idx = statistics_header_info.get(consts.DATE_KEY)
        amount_cell_idx = statistics_header_info.get(consts.AMOUNT_KEY)  # None or src or append
@@ -292,6 +293,10 @@ class BSWorkbook(Workbook):
        outlay_cell_idx = statistics_header_info.get(consts.OUTLAY_KEY)
        borrow_cell_idx = statistics_header_info.get(consts.BORROW_KEY)
        header = list(statistics_header_info.get(consts.HEADER_KEY))
+        src_header_len = len(header)
+        if max_column > src_header_len:
+            for i in range(max_column - src_header_len):
+                header.append(None)
        add_col = ['核对结果']
        if amount_cell_idx is None:
@@ -431,10 +436,12 @@ class BSWorkbook(Workbook):
            classify = summary.get('classify', 0)
            sheet_header_info = {}
            header_info = {}
+            max_column_list = []
            for sheet in summary.get('sheet', []):
                ws = self.get_sheet_by_name(sheet)
-                self.header_collect(ws, sheet_header_info, header_info)
+                self.header_collect(ws, sheet_header_info, header_info, max_column_list)
            statistics_header_info = self.header_statistics(sheet_header_info, header_info, classify)
+            max_column = max(max_column_list)
            # 1.2.按月份分割 min_row 正文第一行 date_col 日期行
            start_date = summary.get('start_date')
@@ -466,7 +473,7 @@ class BSWorkbook(Workbook):
            for month_list in month_mapping.values():
                month_list.sort(key=lambda x: x[-1], reverse=is_reverse)
-            self.build_month_sheet(ms, card, month_mapping, is_reverse, statistics_header_info)
+            self.build_month_sheet(ms, card, month_mapping, is_reverse, statistics_header_info, max_column)
            # 4.删除原表
            for sheet in summary.get('sheet'):