From 11f70ca9b1714dc312a847505c9940f0c60a24b1 Mon Sep 17 00:00:00 2001
From: huzixia <528543747@qq.com>
Date: Sat, 27 Jan 2024 18:06:52 +0800
Subject: [PATCH] modify code based on feedback of action_node.py and
 repair_llm_raw_output.py, add code in test_repair_llm_raw_output.py

---
 metagpt/actions/action_node.py                |  5 +---
 metagpt/utils/repair_llm_raw_output.py        |  9 +------
 .../utils/test_repair_llm_raw_output.py       | 26 +++++++++++++++++++
 3 files changed, 28 insertions(+), 12 deletions(-)

diff --git a/metagpt/actions/action_node.py b/metagpt/actions/action_node.py
index ed0e27869..6c65b33ef 100644
--- a/metagpt/actions/action_node.py
+++ b/metagpt/actions/action_node.py
@@ -23,10 +23,7 @@ from metagpt.utils.common import OutputParser, general_after_log
 TAG = "CONTENT"
 
 LANGUAGE_CONSTRAINT = "Language: Please use the same language as Human INPUT."
-FORMAT_CONSTRAINT = (f"Format: output wrapped inside [{TAG}][/{TAG}] like format example, nothing else. "
-                     f"Delete comments in json")
-# Delete comments in json
-# If you don't want JSONDecodeError to occur, you can add Delete comments in json after FORMAT_CONSTRAINT
+FORMAT_CONSTRAINT = f"Format: output wrapped inside [{TAG}][/{TAG}] like format example, nothing else."
 
 
 SIMPLE_TEMPLATE = """
diff --git a/metagpt/utils/repair_llm_raw_output.py b/metagpt/utils/repair_llm_raw_output.py
index ef3580750..973cffb8a 100644
--- a/metagpt/utils/repair_llm_raw_output.py
+++ b/metagpt/utils/repair_llm_raw_output.py
@@ -137,11 +137,10 @@ def repair_json_format(output: str) -> str:
     elif output.startswith("{") and output.endswith("]"):
         output = output[:-1] + "}"
 
-    # remove comments in output json str, after json value content, maybe start with #, maybe start with //
+    # remove comments in output json string
     arr = output.split("\n")
     new_arr = []
     for line in arr:
-        # look for # or // comments and make sure they are not inside the string value
         new_line = remove_comments_from_line(line)
         new_arr.append(new_line)
     output = "\n".join(new_arr)
@@ -214,12 +213,6 @@ def repair_invalid_json(output: str, error: str) -> str:
             new_line = line.replace("}", "")
         elif line.endswith("},") and output.endswith("},"):
             new_line = line[:-1]
-        # remove comments in output json str, after json value content, maybe start with #, maybe start with //
-        elif rline[col_no] == "#" or rline[col_no] == "/":
-            new_line = rline[:col_no]
-            # check the next line and remove the comments
-            for i in range(line_no + 1, len(arr)):
-                arr[i] = remove_comments_from_line(arr[i])
         elif (rline[col_no] in ["'", '"']) and (line.startswith('"') or line.startswith("'")) and "," not in line:
             # problem, `"""` or `'''` without `,`
             new_line = f",{line}"
diff --git a/tests/metagpt/utils/test_repair_llm_raw_output.py b/tests/metagpt/utils/test_repair_llm_raw_output.py
index 1f809a081..9d53b8243 100644
--- a/tests/metagpt/utils/test_repair_llm_raw_output.py
+++ b/tests/metagpt/utils/test_repair_llm_raw_output.py
@@ -141,6 +141,32 @@ def test_repair_json_format():
     output = repair_llm_raw_output(output=raw_output, req_keys=[None], repair_type=RepairType.JSON)
     assert output == target_output
 
+    raw_output = """
+{
+    "Language": "en_us",  // define language
+    "Programming Language": "Python" # define code language
+}
+"""
+    target_output = """{
+    "Language": "en_us",  
+    "Programming Language": "Python"
+}"""
+    output = repair_llm_raw_output(output=raw_output, req_keys=[None], repair_type=RepairType.JSON)
+    assert output == target_output
+
+    raw_output = """
+    {
+        "Language": "#en_us#",  // define language
+        "Programming Language": "//Python # Code // Language//" # define code language
+    }
+    """
+    target_output = """{
+        "Language": "#en_us#",  
+        "Programming Language": "//Python # Code // Language//"
+    }"""
+    output = repair_llm_raw_output(output=raw_output, req_keys=[None], repair_type=RepairType.JSON)
+    assert output == target_output
+
 
 def test_repair_invalid_json():
     from metagpt.utils.repair_llm_raw_output import repair_invalid_json