github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-11 07:50:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(text-splitters): add Visual Basic 6 support (#31173)

Browse Source 
### **Description**

Add Visual Basic 6 support.

---

### **Issue**

No specific issue addressed.

---

### **Dependencies**

No additional dependencies required.

---------

Co-authored-by: Mason Daugherty <mason@langchain.dev>
This commit is contained in:
Fabio Fontana
2025-07-14 15:51:16 +02:00
committed by GitHub
parent 7e146a185b
commit fd168e1c11
4 changed files with 261 additions and 93 deletions
Download Patch File Download Diff File Expand all files Collapse all files

76
libs/text-splitters/tests/unit_tests/test_text_splitters.py
View File

@@ -3043,6 +3043,82 @@ $csvContent | ForEach-Object {
]
FAKE_VISUALBASIC6_TEXT = """
Option Explicit
Public Function SumTwoIntegers(ByVal a As Integer, ByVal b As Integer) As Integer
SumTwoIntegers = a + b
End Function
Public Sub Main()
Dim i As Integer
Dim limit As Integer
i = 0
limit = 50
While i < limit
i = SumTwoIntegers(i, 1)
If i = limit \\ 2 Then
MsgBox "Halfway there! i = " & i
End If
Wend
MsgBox "Done! Final value of i: " & i
End Sub
"""
def test_visualbasic6_code_splitter() -> None:
splitter = RecursiveCharacterTextSplitter.from_language(
Language.VISUALBASIC6,
chunk_size=CHUNK_SIZE,
chunk_overlap=0,
)
chunks = splitter.split_text(FAKE_VISUALBASIC6_TEXT)
assert chunks == [
"Option Explicit",
"Public Function",
"SumTwoIntegers(",
"ByVal",
"a As Integer,",
"ByVal b As",
"Integer) As",
"Integer",
"SumTwoIntegers",
"= a + b",
"End Function",
"Public Sub",
"Main()",
"Dim i As",
"Integer",
"Dim limit",
"As Integer",
"i = 0",
"limit = 50",
"While i <",
"limit",
"i =",
"SumTwoIntegers(",
"i,",
"1)",
"If i =",
"limit \\ 2 Then",
'MsgBox "Halfway',
'there! i = " &',
"i",
"End If",
"Wend",
"MsgBox",
'"Done! Final',
'value of i: " &',
"i",
"End Sub",
]
def custom_iframe_extractor(iframe_tag: Any) -> str:
iframe_src = iframe_tag.get("src", "")
return f"[iframe:{iframe_src}]({iframe_src})"