From 7ce544ebe7ad1bff5aa3830c576c712e64f7cdbb2435627b10d91185cd1ac7b7 Mon Sep 17 00:00:00 2001
From: PioApocalypse <pioapocalypse@proton.me>
Date: Mon, 26 Jan 2026 10:37:41 +0100
Subject: [PATCH] creates a basic parsing script

---
 tests/scripts/basic_parser.py | 86 +++++++++++++++++++++++++++++++++++
 1 file changed, 86 insertions(+)

diff --git a/tests/scripts/basic_parser.py b/tests/scripts/basic_parser.py
index 473a0f4..5c8e2eb 100644
--- a/tests/scripts/basic_parser.py
+++ b/tests/scripts/basic_parser.py
@@ -0,0 +1,86 @@
+import os, json, requests
+from getpass import getpass
+
+def valid_elabfiles(path):
+    '''Lookup directory "path" and
+       returns list of valid eLabFTW
+       Experiment JSON files.'''
+    elabfiles = []
+    for filename in os.listdir(path):
+        if filename.endswith(".json"):
+            try:
+                with open(os.path.join(path, filename), "r") as f:
+                    data = json.load(f)
+                    if data.get("elabid"): # insert specific NeXus requirements here later
+                        
+                        elabfiles.append(filename)
+                f.close()
+            except json.decoder.JSONDecodeError as e: # invalid files "masked" as JSON
+                #print(f"wait a moment: {e}") # just for debug
+                pass
+    return elabfiles
+
+def call_sample(apikey, elabid, SERVER_URL="https://elabftw.fisica.unina.it/"): # TO-DO: rm default server
+    '''Queries the Resources (/items) API endpoint
+       of eLabFTW instance to request data (JSON)
+       on a certain sample given its eLab-ID.
+       
+       Requires an active (RO/RW) API key.
+       Defaults to elabftw.fisica.unina.it.'''
+    full_elab_url = f"{SERVER_URL}api/v2" # API endpoint root for eLabFTW
+    items_url = f"{full_elab_url}/items" # API endpoint /items
+    header = {
+        "Authorization": apikey,
+        "Content-Type": "application/json"
+    }
+    sample = requests.get(
+        headers=header,
+        url=f"{items_url}/{elabid}",
+        verify=True
+    )
+    return sample.json()
+
+def id2sample(apikey, elabid):
+    '''Fetches sample data (JSON) from eLabFTW
+       instance (using function "call_sample()")
+       and extracts significant information.
+       
+       Currently, it only returns the sample's title.'''
+    #apikey = getpass("Paste API key here: ") # move outside loops
+    sample_data = call_sample(apikey, elabid)
+    sample_title = sample_data["title"]
+    return sample_title
+
+def fetch_and_group(path):
+    '''Fetches experiment data from eLabFTW JSON
+       files in a given folder, then 
+    '''
+    sample_dict = {}
+    apikey = getpass("Paste API key here: ")
+    for filename in valid_elabfiles(path):
+        with open(os.path.join(path, filename), "r") as f:
+            layer = json.load(f)
+            extra = layer["metadata_decoded"]["extra_fields"]
+            sample_id = extra["Sample"]["value"]
+            sample_title = id2sample(apikey, sample_id)
+            lpn = int(extra["Layer Progressive Number"]["value"]) # Layer Progressive Number
+            if not sample_dict.get(sample_title): # if not existent yet, initialize
+                sample_dict[sample_title] = {
+                    "instrument": {
+                        "deposition_chamber": extra["Chamber"]["value"], # ID of associated resource (PLD chamber) - useless as is!
+                        "laser_system": extra["Laser System"]["value"],
+                        "rheed_system": extra["RHEED System"]["value"]
+                    },
+                    "multilayer": {}
+                    }
+            sample_dict[sample_title]["multilayer"][f"layer_{lpn}"] = {
+                "operator": layer["fullname"],
+                "created_at": layer["created_at"],
+                "sample": extra["Sample"], # ID of associated sample - useless as is!
+                "temperature": extra["Heater temperature "], # space at the end is a config error in eLab!
+                "target": extra["Target"]
+            }
+    return sample_dict
+
+sample_dict = fetch_and_group("./tests/objects")
+print(json.dumps(sample_dict, indent=3))
\ No newline at end of file