From 560e13d1c28a32e5ca8af5862d6d7da7eaa5739f Mon Sep 17 00:00:00 2001
From: Michal Zoubek <michal.zoubek@prusa3d.cz>
Date: Mon, 28 Aug 2023 16:02:43 +0200
Subject: [PATCH] Obtaining metadata from path rewritten to function with
 separated regexes

---
 gcode_metadata/metadata.py | 64 +++++++++++++++++++++++++++++---------
 1 file changed, 50 insertions(+), 14 deletions(-)

diff --git a/gcode_metadata/metadata.py b/gcode_metadata/metadata.py
index 1b5c7b6..4fc5590 100644
--- a/gcode_metadata/metadata.py
+++ b/gcode_metadata/metadata.py
@@ -99,6 +99,53 @@ def same_or_nothing(value_list):
     return value_list[0]
 
 
+def extract_data(input_string):
+    """Extracts metadata from the filename
+        >>> extract_data("MP_PLA,PLA_MK3SMMU3_3h22m.gcode")
+        {'name': 'MP_', 'nozzle': None, 'height': None, 'material': 'PLA', 'printer': 'MK3SMMU3', 'time': '3h22m'}
+        >>> extract_data("sh_bn_0.6n_0.32mm_PETG_MK4_8h55m.gcode")
+        {'name': 'sh_bn_', 'nozzle': '0.6n', 'height': '0.32mm', 'material': 'PETG', 'printer': 'MK4', 'time': '8h55m'}
+        >>> extract_data("PLA_0.6n 0.32mm_MK3S_1d1h42m.gcode")
+        {'name': '', 'nozzle': '0.6n', 'height': '0.32mm', 'material': 'PLA', 'printer': 'MK3S', 'time': '1d1h42m'}
+    """
+    printer_enum = [
+        'MK4IS', 'MK4MMU3', 'MK4', 'MK3SMMU3', 'MK3MMU3', 'MK3SMMU2S',
+        'MK3MMU2', 'MK3S', 'MK3', 'MK2.5SMMU2S', 'MK2.5MMU2', 'MK2.5S',
+        'MK2.5', 'MINI', 'XL5', 'XL4', 'XL3', 'XL2', 'XL', 'iX', 'SL1',
+        'SHELF', 'DeltiQ 2 Plus', 'DeltiQ 2', 'AzteQ Industrial Plus',
+        'AzteQ Industrial', 'AzteQ', 'EXTRACTOR', 'HARVESTER'
+    ]
+
+    printer_enum.sort(key=len, reverse=True)
+
+    material_enum = [
+        'PLA', 'PETG', 'ABS', 'ASA', 'FLEX', 'HIPS', 'EDGE', 'NGEN', 'PA',
+        'PVA', 'PCTG', 'PP', 'PC', 'TPU', 'PEBA', 'CPE', 'PVB', 'PET'
+    ]
+
+    patterns = [
+        (r"(.*?)(?=[0-9.]+n|mm|{material_enum_pattern}|{printer_enum_pattern}|\d+[dhm]+)",
+         'name'),
+        (r"([0-9.]+)n", 'nozzle'),
+        (r"([0-9.]+)mm", 'height'),
+        (r"(?:" + "|".join(material_enum) + r")", 'material'),
+        (r"(?:" + "|".join(printer_enum) + r")", 'printer'),
+        (r"(\d+[dhm]+(?:\d*[dhm]+)*)(?!\w)", 'time')
+    ]
+
+    material_enum_pattern = "|".join(material_enum)
+    printer_enum_pattern = "|".join(printer_enum)
+
+    data = {}
+    for pattern, key in patterns:
+        pattern = pattern.format(material_enum_pattern=material_enum_pattern,
+                                 printer_enum_pattern=printer_enum_pattern)
+        match = re.search(pattern, input_string)
+        data[key] = match.group() if match else None
+
+    return data
+
+
 class MetaData:
     """Base MetaData class"""
 
@@ -363,10 +410,6 @@ def set_attr(self, name, value):
         "normal_change_in": "normal_change_in_present"
     }
 
-    FDM_FILENAME_PAT = re.compile(
-        r"^(?P<name>.*?)_(?P<height>[0-9.]+)mm_(?P<material>[A-Za-z]+)_"
-        r"(?P<printer>[A-Za-z0-9]+)_(?P<time>[A-Za-z0-9]+)_?\w*.")
-
     METADATA_START_OFFSET = 400000  # Read 400KB from the start
     METADATA_END_OFFSET = 40000  # Read 40KB at the end of the file
     # Number of times the search for M73 is going to repeat if info
@@ -390,16 +433,9 @@ def __init__(self, path: str):
     def load_from_path(self, path):
         """Try to obtain any usable metadata from the path itself"""
         filename = os.path.basename(path)
-        match = self.FDM_FILENAME_PAT.match(filename)
-        if match:
-            data = {
-                "name": match.group("name"),
-                "layer_height": match.group("height"),
-                "filament_type": match.group("material"),
-                "printer_model": match.group("printer"),
-                "estimated printing time (normal mode)": match.group("time"),
-            }
-            self.set_data(data)
+
+        data = extract_data(filename)
+        self.set_data(data)
 
     def from_comment_line(self, line):
         """Parses data from a line in the comments"""