Update app.py

app.py

@@ -11,8 +11,6 @@ import os
 
 #  Define source folder and console outpiut colors
 folder_path = r"C:\Users\match\Downloads"
-CEND = '\033[0m'
-CRED = '\033[91m'
 
 # ------------------------------------------------
 # 1) Amino-acid dictionary (neutral, free AA)
@@ -977,33 +975,6 @@ def clean_file_contents(file_contents):
 
     return ' '.join(re.sub(r'\[\d+\]', '', file_contents).split()).strip()
 
-# Specify the dictionary file name
-file_name = "chemical_data.txt"
-
-# Initialize an empty dictionary
-chemical_dict = {}
-
-# Load the dictionary from the file
-try:
-    with open(file_name, "r", encoding="utf-8") as file:  # Explicit UTF-8 encoding
-        for line in file:
-            # Split each line into key and value
-            parts = line.strip().split(":")
-
-            if len(parts) == 2:
-                # Extract key and value
-                chemical = parts[0].strip()
-                formula = parts[1].strip()
-                # Add to the dictionary
-                chemical_dict[chemical] = formula
-except FileNotFoundError:
-    print(f"File '{file_name}' not found. Make sure the file exists.")
-except UnicodeDecodeError:
-    print(f"Encoding issue detected. Try opening '{file_name}' with a different encoding.")
-
-# Print the loaded dictionary
-print("Loaded Dictionary: chemical_dict.txt")
-
 
 def check_reagents(pdf_file_path):
     """
@@ -1022,14 +993,11 @@ def check_reagents(pdf_file_path):
         file_contents = clean_file_contents(file_contents)
 
         # search for the following pattern "x mg Y (z mmol" where Y is a string and x and z are float or integer and transform it into "Y (x mg, z mmol)"
-
         pattern = r"(\d+\.?\d*) mg ([a-zA-Z0-9-]+) \((\d+\.?\d*) mmol\)"
 
-        # Function to transform the string
         def transform_string(s):
             return re.sub(pattern, r"\2 (\1 mg, \3 mmol)", s)
 
-        # Transform file_contents string
         file_contents = transform_string(file_contents)
         result = extract_values_from_text(file_contents)
         x, y, z = extract_info_from_list(result)
@@ -1037,13 +1005,12 @@ def check_reagents(pdf_file_path):
         if x:
             for i in range(len(x)):
                 if x[i]:
-
                     if z[i] != 0:
                         apparent_mw = y[i] / z[i]
                     else:
                         apparent_mw = 1000.66
                     mw = None
-                    words = x[i].split()  # Line 1: Split the string into a list of words
+                    words = x[i].split()
                     if words and len(words[0]) > 4:
                         formula_from_name = name_to_sum_formula(x[i])
                     else:
@@ -1061,10 +1028,7 @@ def check_reagents(pdf_file_path):
                     if mw:
                         mass_error = abs(round(((mw / apparent_mw) - 1) * 100, 1))
                         error_msg = f"{x[i]} ({y[i]} mg, {z[i]} mmol) MW: {mw}, used: {apparent_mw:.2f} (Mass error: {mass_error}{'%)' + (' *' if formula_from_name else '')}"
-                        if mass_error > 10:
-                            reagent_errors.append(f"{CRED}{error_msg}{CEND}")
-                        else:
-                            reagent_errors.append(error_msg)
+                        reagent_errors.append(error_msg)
 
                     if not mw:
                         x[i] = remove_first_word(x[i])
@@ -1089,10 +1053,7 @@ def check_reagents(pdf_file_path):
                             if mw:
                                 mass_error = abs(round(((mw / apparent_mw) - 1) * 100, 1))
                                 error_msg = f"{x[i]} ({y[i]} mg, {z[i]} mmol) MW: {mw}, used: {apparent_mw:.2f} (Mass error: {mass_error}{'%' + (' *' if formula_from_name else '')})"
-                                if mass_error > 10:
-                                    reagent_errors.append(f"{CRED}{error_msg}{CEND}")
-                                else:
-                                    reagent_errors.append(error_msg)
+                                reagent_errors.append(error_msg)
 
                     if not mw:
                         x[i] = remove_first_word(x[i])
@@ -1121,10 +1082,7 @@ def check_reagents(pdf_file_path):
                             if mw and mw != 666.66:
                                 mass_error = abs(round(((mw / apparent_mw) - 1) * 100, 1))
                                 error_msg = f"{x[i]} ({y[i]} mg, {z[i]} mmol) MW: {mw}, used: {apparent_mw:.2f} (Mass error: {mass_error}{'%)' + (' *' if formula_from_name else '')}"
-                                if mass_error > 10:
-                                    reagent_errors.append(f"{CRED}{error_msg}{CEND}")
-                                else:
-                                    reagent_errors.append(error_msg)
+                                reagent_errors.append(error_msg)
 
                     if not mw:
                         x[i] = remove_first_word(x[i])
@@ -1165,122 +1123,45 @@ def check_reagents(pdf_file_path):
                             if mw and mw != 666.66:
                                 mass_error = abs(round(((mw / apparent_mw) - 1) * 100, 1))
                                 error_msg = f"{x[i]} ({y[i]} mg, {z[i]} mmol) MW: {mw}, used: {apparent_mw:.2f} (Mass error: {mass_error}{'%)' + (' *' if formula_from_name or replacement_formula else '')}"
-                                if mass_error > 10:
-                                    reagent_errors.append(f"{CRED}{error_msg}{CEND}")
-                                else:
-                                    reagent_errors.append(error_msg)
+                                reagent_errors.append(error_msg)
 
     except Exception as e:
-        # Handle the error, or simply return error info
         reagent_errors.append(f"an error occurred: {e}")
 
     return reagent_errors
 
-def clean_ansi_codes(text):
-    """
-    Remove ANSI escape codes from text and return clean text.
-    """
-    ansi_escape = re.compile(r'\x1B(?:[@-Z\\-_]|\[[0-?]*[ -/]*[@-~])')
-    return ansi_escape.sub('', text)
 
-def format_reagent_error(error_text):
-    """
-    Format reagent error text for Streamlit display.
-    Converts ANSI color codes to appropriate Streamlit styling.
-    """
-    # Clean the text of ANSI codes
-    clean_text = clean_ansi_codes(error_text)
-    
-    # Check if the original text had red color codes (indicating an error/warning)
-    has_red_color = '\033[91m' in error_text or '[91m' in error_text
-    has_asterisk = '*' in error_text
-    
-    return clean_text, has_red_color, has_asterisk
 
-def check_reagents(pdf_file_path):
-    """
-    Replace this entire function with your actual implementation.
-    """
-    # This is just a placeholder - replace with your real function
-    return []  # Returns empty list so no fake errors show
 
-def clean_ansi_codes(text):
-    """
-    Remove ANSI escape codes from text and return clean text.
-    """
-    ansi_escape = re.compile(r'\x1B(?:[@-Z\\-_]|\[[0-?]*[ -/]*[@-~])')
-    return ansi_escape.sub('', text)
 
-def format_reagent_error(error_text):
-    """
-    Format reagent error text for Streamlit display.
-    Converts ANSI color codes and determines if mass error >= 10%.
-    """
-    # Clean the text of ANSI codes
-    clean_text = clean_ansi_codes(error_text)
-    
-    # Extract mass error percentage using regex
-    mass_error_pattern = r'Mass error:\s*(\d+\.?\d*)%'
-    match = re.search(mass_error_pattern, clean_text)
-    
-    is_high_error = False
-    if match:
-        mass_error_percent = float(match.group(1))
-        is_high_error = mass_error_percent >= 10.0
-    
-    return clean_text, is_high_error
+# Specify the dictionary file name
+file_name = "chemical_data.txt"
 
-def clean_ansi_codes(text):
-    """
-    Remove ANSI escape codes from text and return clean text.
-    """
-    ansi_escape = re.compile(r'\x1B(?:[@-Z\\-_]|\[[0-?]*[ -/]*[@-~])')
-    return ansi_escape.sub('', text)
+# Initialize an empty dictionary
+chemical_dict = {}
 
-def format_reagent_error(error_text):
-    """
-    Format reagent error text for Streamlit display.
-    Converts ANSI color codes and determines if mass error >= 10%.
-    """
-    # Clean the text of ANSI codes
-    clean_text = clean_ansi_codes(error_text)
-    
-    # Extract mass error percentage using regex
-    mass_error_pattern = r'Mass error:\s*(\d+\.?\d*)%'
-    match = re.search(mass_error_pattern, clean_text)
-    
-    is_high_error = False
-    if match:
-        mass_error_percent = float(match.group(1))
-        is_high_error = mass_error_percent >= 10.0
-    
-    return clean_text, is_high_error
+# Load the dictionary from the file
+try:
+    with open(file_name, "r", encoding="utf-8") as file:  # Explicit UTF-8 encoding
+        for line in file:
+            # Split each line into key and value
+            parts = line.strip().split(":")
+
+            if len(parts) == 2:
+                # Extract key and value
+                chemical = parts[0].strip()
+                formula = parts[1].strip()
+                # Add to the dictionary
+                chemical_dict[chemical] = formula
+except FileNotFoundError:
+    print(f"File '{file_name}' not found. Make sure the file exists.")
+except UnicodeDecodeError:
+    print(f"Encoding issue detected. Try opening '{file_name}' with a different encoding.")
+
+# Print the loaded dictionary
+print("Loaded Dictionary: chemical_dict.txt")
 
-def clean_ansi_codes(text):
-    """
-    Remove ANSI escape codes from text and return clean text.
-    """
-    ansi_escape = re.compile(r'\x1B(?:[@-Z\\-_]|\[[0-?]*[ -/]*[@-~])')
-    return ansi_escape.sub('', text)
 
-def format_reagent_error(error_text):
-    """
-    Format reagent error text for Streamlit display.
-    Converts ANSI color codes and determines if mass error >= 10%.
-    """
-    # Clean the text of ANSI codes
-    clean_text = clean_ansi_codes(error_text)
-    
-    # Extract mass error percentage using regex
-    mass_error_pattern = r'Mass error:\s*(\d+\.?\d*)%'
-    match = re.search(mass_error_pattern, clean_text)
-    
-    is_high_error = False
-    if match:
-        mass_error_percent = float(match.group(1))
-        is_high_error = mass_error_percent >= 10.0
-    
-    return clean_text, is_high_error
 
 def main():
     st.set_page_config(