Fix `invalid escape sequence` warnings by using raw strings for regexes. (#11943)

This code also generates warnings when our users' apps hit it, which is
annoying and doesn't look great. Let's fix it.

libs/langchain/langchain/chains/query_constructor/parser.py

@@ -23,7 +23,7 @@ from langchain.chains.query_constructor.ir import (
     Operator,
 )
 
-GRAMMAR = """
+GRAMMAR = r"""
     ?program: func_call
     ?expr: func_call
         | value

libs/langchain/langchain/document_loaders/acreom.py

@@ -49,9 +49,9 @@ class AcreomLoader(BaseLoader):
     def _process_acreom_content(self, content: str) -> str:
         # remove acreom specific elements from content that
         # do not contribute to the context of current document
-        content = re.sub("\s*-\s\[\s\]\s.*|\s*\[\s\]\s.*", "", content)  # rm tasks
-        content = re.sub("#", "", content)  # rm hashtags
-        content = re.sub("\[\[.*?\]\]", "", content)  # rm doclinks
+        content = re.sub(r"\s*-\s\[\s\]\s.*|\s*\[\s\]\s.*", "", content)  # rm tasks
+        content = re.sub(r"#", "", content)  # rm hashtags
+        content = re.sub(r"\[\[.*?\]\]", "", content)  # rm doclinks
         return content
 
     def lazy_load(self) -> Iterator[Document]:

libs/langchain/langchain/document_transformers/openai_functions.py

@@ -40,7 +40,7 @@ class OpenAIMetadataTagger(BaseDocumentTransformer, BaseModel):
                 tagging_chain = create_tagging_chain(schema, llm)
                 document_transformer = OpenAIMetadataTagger(tagging_chain=tagging_chain)
                 original_documents = [
-                    Document(page_content="Review of The Bee Movie\nBy Roger Ebert\n\This is the greatest movie ever made. 4 out of 5 stars."),
+                    Document(page_content="Review of The Bee Movie\nBy Roger Ebert\n\nThis is the greatest movie ever made. 4 out of 5 stars."),
                     Document(page_content="Review of The Godfather\nBy Anonymous\n\nThis movie was super boring. 1 out of 5 stars.", metadata={"reliable": False}),
                 ]
 
@@ -123,7 +123,7 @@ def create_metadata_tagger(
 
                 document_transformer = create_metadata_tagger(schema, llm)
                 original_documents = [
-                    Document(page_content="Review of The Bee Movie\nBy Roger Ebert\n\This is the greatest movie ever made. 4 out of 5 stars."),
+                    Document(page_content="Review of The Bee Movie\nBy Roger Ebert\n\nThis is the greatest movie ever made. 4 out of 5 stars."),
                     Document(page_content="Review of The Godfather\nBy Anonymous\n\nThis movie was super boring. 1 out of 5 stars.", metadata={"reliable": False}),
                 ]
 

libs/langchain/langchain/retrievers/kendra.py

@@ -20,7 +20,7 @@ def clean_excerpt(excerpt: str) -> str:
     """
     if not excerpt:
         return excerpt
-    res = re.sub("\s+", " ", excerpt).replace("...", "")
+    res = re.sub(r"\s+", " ", excerpt).replace("...", "")
     return res
 
 
@@ -45,7 +45,7 @@ def combined_text(item: "ResultItem") -> str:
 
 
 DocumentAttributeValueType = Union[str, int, List[str], None]
-"""Possible types of a DocumentAttributeValue. 
+"""Possible types of a DocumentAttributeValue.
 
 Dates are also represented as str.
 """

libs/langchain/langchain/retrievers/self_query/myscale.py

@@ -88,8 +88,8 @@ class MyScaleTranslator(Visitor):
         return self.map_dict[func](*args)
 
     def visit_comparison(self, comparison: Comparison) -> Dict:
-        regex = "\((.*?)\)"
-        matched = re.search("\(\w+\)", comparison.attribute)
+        regex = r"\((.*?)\)"
+        matched = re.search(r"\(\w+\)", comparison.attribute)
 
         # If arbitrary function is applied to an attribute
         if matched:

libs/langchain/langchain/utils/html.py

@@ -18,13 +18,13 @@ SUFFIXES_TO_IGNORE = (
     ".epub",
 )
 SUFFIXES_TO_IGNORE_REGEX = (
-    "(?!" + "|".join([re.escape(s) + "[\#'\"]" for s in SUFFIXES_TO_IGNORE]) + ")"
+    "(?!" + "|".join([re.escape(s) + r"[\#'\"]" for s in SUFFIXES_TO_IGNORE]) + ")"
 )
 PREFIXES_TO_IGNORE_REGEX = (
     "(?!" + "|".join([re.escape(s) for s in PREFIXES_TO_IGNORE]) + ")"
 )
 DEFAULT_LINK_REGEX = (
-    f"href=[\"']{PREFIXES_TO_IGNORE_REGEX}((?:{SUFFIXES_TO_IGNORE_REGEX}.)*?)[\#'\"]"
+    rf"href=[\"']{PREFIXES_TO_IGNORE_REGEX}((?:{SUFFIXES_TO_IGNORE_REGEX}.)*?)[\#'\"]"
 )