Format file format from Windows/dos to Unix (#1949)

### What problem does this PR solve? Related source file is in Windows/DOS format, they are format to Unix format. ### Type of change - [x] Refactoring Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2025-12-08 20:42:30 +08:00 · 2024-08-15 09:17:36 +08:00
parent 1328d715db
commit 6b3a40be5c
108 changed files with 36399 additions and 36399 deletions
--- a/deepdoc/parser/ppt_parser.py
+++ b/deepdoc/parser/ppt_parser.py
@ -1,61 +1,61 @@
-#  Licensed under the Apache License, Version 2.0 (the "License");
-#  you may not use this file except in compliance with the License.
-#  You may obtain a copy of the License at
-#
-#      http://www.apache.org/licenses/LICENSE-2.0
-#
-#  Unless required by applicable law or agreed to in writing, software
-#  distributed under the License is distributed on an "AS IS" BASIS,
-#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-#  See the License for the specific language governing permissions and
-#  limitations under the License.
-#
-
-from io import BytesIO
-from pptx import Presentation
-
-
-class RAGFlowPptParser(object):
-    def __init__(self):
-        super().__init__()
-
-    def __extract(self, shape):
-        if shape.shape_type == 19:
-            tb = shape.table
-            rows = []
-            for i in range(1, len(tb.rows)):
-                rows.append("; ".join([tb.cell(
-                    0, j).text + ": " + tb.cell(i, j).text for j in range(len(tb.columns)) if tb.cell(i, j)]))
-            return "\n".join(rows)
-
-        if shape.has_text_frame:
-            return shape.text_frame.text
-
-        if shape.shape_type == 6:
-            texts = []
-            for p in sorted(shape.shapes, key=lambda x: (x.top // 10, x.left)):
-                t = self.__extract(p)
-                if t:
-                    texts.append(t)
-            return "\n".join(texts)
-
-    def __call__(self, fnm, from_page, to_page, callback=None):
-        ppt = Presentation(fnm) if isinstance(
-            fnm, str) else Presentation(
-            BytesIO(fnm))
-        txts = []
-        self.total_page = len(ppt.slides)
-        for i, slide in enumerate(ppt.slides):
-            if i < from_page:
-                continue
-            if i >= to_page:
-                break
-            texts = []
-            for shape in sorted(
-                    slide.shapes, key=lambda x: ((x.top if x.top is not None else 0) // 10, x.left)):
-                txt = self.__extract(shape)
-                if txt:
-                    texts.append(txt)
-            txts.append("\n".join(texts))
-
-        return txts
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+#
+
+from io import BytesIO
+from pptx import Presentation
+
+
+class RAGFlowPptParser(object):
+    def __init__(self):
+        super().__init__()
+
+    def __extract(self, shape):
+        if shape.shape_type == 19:
+            tb = shape.table
+            rows = []
+            for i in range(1, len(tb.rows)):
+                rows.append("; ".join([tb.cell(
+                    0, j).text + ": " + tb.cell(i, j).text for j in range(len(tb.columns)) if tb.cell(i, j)]))
+            return "\n".join(rows)
+
+        if shape.has_text_frame:
+            return shape.text_frame.text
+
+        if shape.shape_type == 6:
+            texts = []
+            for p in sorted(shape.shapes, key=lambda x: (x.top // 10, x.left)):
+                t = self.__extract(p)
+                if t:
+                    texts.append(t)
+            return "\n".join(texts)
+
+    def __call__(self, fnm, from_page, to_page, callback=None):
+        ppt = Presentation(fnm) if isinstance(
+            fnm, str) else Presentation(
+            BytesIO(fnm))
+        txts = []
+        self.total_page = len(ppt.slides)
+        for i, slide in enumerate(ppt.slides):
+            if i < from_page:
+                continue
+            if i >= to_page:
+                break
+            texts = []
+            for shape in sorted(
+                    slide.shapes, key=lambda x: ((x.top if x.top is not None else 0) // 10, x.left)):
+                txt = self.__extract(shape)
+                if txt:
+                    texts.append(txt)
+            txts.append("\n".join(texts))
+
+        return txts