bella-openapi 1.0.2.5__py3-none-any.whl → 1.0.3.1__py3-none-any.whl

bella_openapi/__init__.py

@@ -3,19 +3,8 @@ from .log import operation_log, submit_log
 from .openapi_contexvar import trace_id_context, caller_id_context, request_url_context
 from .auth_billing import ErrorInfo, async_authenticate_decorator_args, authenticate_user, print_context, \
 get_context, set_context, clean_context, report
-from .entity import (
-    StandardDomTree,
-    StandardNode,
-    SourceFile,
-    StandardPosition,
-    StandardImage,
-    Cell,
-    StandardRow,
-    StandardBaseElement,
-    StandardElement,
-    StandardTableElement,
-    StandardImageElement
-)
+from .entity import StandardDomTree, StandardNode, SourceFile, StandardPosition, StandardImage, Cell, \
+    StandardRow, StandardBaseElement, StandardElement, StandardTableElement, StandardImageElement
 
 __all__ = ["validate_token", "operation_log",
            "support_model",

bella_openapi/entity/standard_domtree.py

@@ -129,7 +129,7 @@ class StandardDomTree(BaseModel):
                     # 添加表格名称
                     if node.element.name:
                         markdown_res += f"**{node.element.name}**\n\n"
-                    table_md = self._list_to_html_table(node.element.rows)
+                    table_md = self._list_to_markdown_table(node.element.rows)
                     markdown_res += f"{table_md}\n\n"
                     # 添加表格描述
                     if node.element.description:
@@ -168,28 +168,25 @@ class StandardDomTree(BaseModel):
         quoted_lines = ['> ' + line for line in lines]
         return '\n'.join(quoted_lines)
 
-    def _list_to_html_table(self, rows: List[StandardRow]) -> str:
-        """将表格行转换为HTML表格"""
+    def _list_to_markdown_table(self, rows: List[StandardRow]) -> str:
+        """将表格行转换为 markdown 表格格式"""
         if not rows:
             return ""
 
-        html_text = "<table>"
+        markdown_table = ""
+
+        # 添加表头
+        if rows:
+            header_cells = [cell.text or "" for cell in rows[0].cells]
+            markdown_table += "| " + " | ".join(header_cells) + " |\n"
+            markdown_table += "| " + " | ".join(["---"] * len(header_cells)) + " |\n"
+
+        # 添加数据行
         for row in rows:
-            html_text += "<tr>"
-            for cell in row.cells:
-                # 从path中提取rowspan和colspan信息
-                if len(cell.path) >= 4:
-                    start_row, end_row, start_col, end_col = cell.path[:4]
-                    rowspan = end_row - start_row + 1
-                    colspan = end_col - start_col + 1
-                else:
-                    rowspan = colspan = 1
+            cells = [cell.text or "" for cell in row.cells]
+            markdown_table += "| " + " | ".join(cells) + " |\n"
 
-                cell_text = cell.text or ""
-                html_text += f"<td rowspan='{rowspan}' colspan='{colspan}'>{cell_text}</td>"
-            html_text += "</tr>"
-        html_text += "</table>"
-        return html_text
+        return markdown_table
 
     @classmethod
     def from_domtree_dict(cls, domtree: dict, file_info):
@@ -306,18 +303,16 @@ class StandardDomTree(BaseModel):
                 # 检查前一个节点
                 if i > 0:
                     prev_sibling = node.children[i - 1]
-                    if prev_sibling.element and prev_sibling.element.type == target_type:
-                        # 找到对应类型的前一个兄弟节点，合并节点
-                        if cls._merge_nodes(prev_sibling, current, target_type):
-                            merged = True
+                    # 找到对应类型的前一个兄弟节点，合并节点
+                    merged = ( prev_sibling.element and prev_sibling.element.type == target_type and
+                               cls._merge_nodes(prev_sibling, current, target_type))
 
                 # 如果没有与前一个节点合并，检查后一个节点
                 if not merged and i < len(node.children) - 1:
                     next_sibling = node.children[i + 1]
-                    if next_sibling.element and next_sibling.element.type == target_type:
-                        # 找到对应类型的后一个兄弟节点，合并节点
-                        if cls._merge_nodes(next_sibling, current, target_type):
-                            merged = True
+                    # 找到对应类型的后一个兄弟节点，合并节点
+                    merged = (next_sibling.element and next_sibling.element.type == target_type and
+                              cls._merge_nodes(next_sibling, current, target_type))
 
                 # 如果没有找到对应类型的兄弟节点，将当前节点类型改为 Text
                 if not merged:
@@ -348,23 +343,25 @@ class StandardDomTree(BaseModel):
         Returns:
             bool: 是否成功合并
         """
-        if node_type == 'Figure' and isinstance(target_node.element, StandardImageElement):
-            # 将 FigureName 的文本作为 Figure 的 name
-            target_node.element.name = source_node.element.text
-            # 更新 tokens 计数
-            target_node.tokens += source_node.tokens
-            # 将 FigureName 的位置添加到 Figure 中
-            target_node.element.positions += source_node.element.positions
-            return True
-        elif node_type == 'Table' and isinstance(target_node.element, StandardTableElement):
-            # 将 TableName 的文本作为 Table 的 name
+        # 定义节点类型与元素类型的映射
+        type_element_mapping = {
+            'Figure': StandardImageElement,
+            'Table': StandardTableElement
+        }
+
+        can_merge = (node_type in type_element_mapping and
+            isinstance(target_node.element, type_element_mapping[node_type]))
+
+        # 检查节点类型是否支持且目标节点元素类型匹配
+        if can_merge:
+            # 将源节点的文本作为目标节点的 name
             target_node.element.name = source_node.element.text
             # 更新 tokens 计数
             target_node.tokens += source_node.tokens
-            # 将 Table 的位置添加到 Figure 中
+            # 将源节点的位置添加到目标节点中
             target_node.element.positions += source_node.element.positions
-            return True
-        return False
+
+        return can_merge
 
     @classmethod
     def _from_domtree_node_to_base_info(cls, node: dict) -> Optional[StandardNode]:
@@ -492,17 +489,17 @@ class StandardDomTree(BaseModel):
         return standard_node
 
     @classmethod
-    def count_tokens(cls, text: str, model: str = "gpt-4") -> int:
+    def count_tokens(cls, text: str) -> int:
         """
         计算文本的token数量
 
         Args:
             text: 要计算的文本
-            model: 使用的模型名称，默认为gpt-4
 
         Returns:
             int: token数量
         """
+        model = "gpt-4" # 使用模型默认为gpt-4
         if not text:
             return 0
         encoding = tiktoken.encoding_for_model(model)

{bella_openapi-1.0.2.5.dist-info → bella_openapi-1.0.3.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: bella-openapi
-Version: 1.0.2.5
+Version: 1.0.3.1
 Summary: client for openapi service.
 Home-page: 
 Author: ['tangxiaolong', 'fanqiangwei', 'zhangxiaojia', 'liumin', 'wangyukun']
@@ -12,6 +12,7 @@ License-File: LICENSE
 Requires-Dist: httpx<=0.26.0,>=0.10.0
 Requires-Dist: Werkzeug==3.0.1
 Requires-Dist: tiktoken>=0.5.0
+Requires-Dist: pydantic==2.11.7
 Dynamic: author
 Dynamic: classifier
 Dynamic: description

{bella_openapi-1.0.2.5.dist-info → bella_openapi-1.0.3.1.dist-info}/RECORD

@@ -1,4 +1,4 @@
-bella_openapi/__init__.py,sha256=Iq8YjMYBNWJvQvlu9gFy8uxG8Xf06jPaCyZvXtAW2jA,1462
+bella_openapi/__init__.py,sha256=RBVZURWQwmb8dN7S6cgDej29bcg_EiHhCmpx1qQMgnw,1420
 bella_openapi/auth_billing.py,sha256=Hn0KS8GuG48etnvnd1Faej4IfFXD3tjzalUzDnpZh7Q,3520
 bella_openapi/authorize.py,sha256=cO6J-wx9dmmkDAeqpXT7QlyCr13hO-HSC5SWQSw2gZw,2150
 bella_openapi/config.py,sha256=Dn8vnToDaOesPGboauxCCwNrW5awQLeSkmDjNjXS4bQ,319
@@ -14,11 +14,11 @@ bella_openapi/bella_trace/trace_requests.py,sha256=ADA8J_gbC3TwUo5LWQ3c_yTmCSZRa
 bella_openapi/console/__init__.py,sha256=uSfr5v6JLRSqTlftjK_ZU1pnbkEyxAPbuQbMyYX_phk,64
 bella_openapi/console/models.py,sha256=Hh1UuYHIxFtF9r5QK-pSJPFrSqbZUHv6spLvPbCeX08,1274
 bella_openapi/entity/__init__.py,sha256=zzsYYg859pzPSgx1Py2kxB2ozQ0tt4OtTatBtpm2bAw,512
-bella_openapi/entity/standard_domtree.py,sha256=EzeYH_UH8MfcVucOcviof8qAIZ5BULVu2DO2EBN7F-c,20510
+bella_openapi/entity/standard_domtree.py,sha256=yJ2FN3xwhT_SPbQSuvMlIvESmjNdQgcu2hzalDq9Gcs,20099
 bella_openapi/middleware/__init__.py,sha256=XWvZG1xO30ZXIn10YVYthmT1BV-9fonMEP_jVRZbAlQ,157
 bella_openapi/middleware/context_middleware.py,sha256=YawQyKAxMzvlDs_MxcuQKh90pP6VoMKzCBDS94qmlzQ,3870
-bella_openapi-1.0.2.5.dist-info/licenses/LICENSE,sha256=O-0zMbcEi6wXz1DiSdVgzMlQjJcNqNe5KDv08uYzqR0,1055
-bella_openapi-1.0.2.5.dist-info/METADATA,sha256=ohCbeW5mv4uFMn3NgoscDQxEBKW7zi168nRfIbgltc0,9377
-bella_openapi-1.0.2.5.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-bella_openapi-1.0.2.5.dist-info/top_level.txt,sha256=EZuq3F6tKeF-vmZQi6_S2XzmES7SPW7HAbGN1Uv9vN8,14
-bella_openapi-1.0.2.5.dist-info/RECORD,,
+bella_openapi-1.0.3.1.dist-info/licenses/LICENSE,sha256=O-0zMbcEi6wXz1DiSdVgzMlQjJcNqNe5KDv08uYzqR0,1055
+bella_openapi-1.0.3.1.dist-info/METADATA,sha256=9td_a-VIyt3wOFv03zo5b_reHr8qLleSxGM9wJflCno,9409
+bella_openapi-1.0.3.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+bella_openapi-1.0.3.1.dist-info/top_level.txt,sha256=EZuq3F6tKeF-vmZQi6_S2XzmES7SPW7HAbGN1Uv9vN8,14
+bella_openapi-1.0.3.1.dist-info/RECORD,,