updating chemError pages to include links to websites to manually resolve SMILES

CHRIS.py

@@ -1,7 +1,35 @@
 from flask import Flask, render_template
+from werkzeug.middleware.profiler import ProfilerMiddleware
 
 app = Flask(__name__)
-app.debug = False
+app.debug = True
+
+# Profile every request (or limit with restrictions)
+#app.wsgi_app = ProfilerMiddleware(
+#    app.wsgi_app,
+#    restrictions=[30],   # show top 30 lines
+#    sort_by=("tottime",) # total time spent in function body
+#)
+
+## DEBUGGING
+if 0:
+    from pprint import pformat
+    from flask import g, request
+
+    @app.after_request
+    def dump_chem_trace(response):
+        trace = getattr(g, "chem_trace", None)
+        if trace:
+            bases = sorted(set(getattr(g, "chem_bases", [])))
+            payload = {
+                "path": request.path,
+                "query": request.values.to_dict(flat=False),
+                "base_urls": bases,
+                "remote_trace": [x for x in trace if x.get("kind") == "remote"],
+                "app_trace": [x for x in trace if x.get("kind") == "app"],
+            }
+            app.logger.warning("CHEMTRACE\n%s", pformat(payload, sort_dicts=False, width=120))
+        return response
 
 #from color_module import blueprint
 #app.register_blueprint(blueprint)

ChemID.py

@@ -13,6 +13,178 @@ import urllib
 import requests
 import json
 
+if 0:
+    ## DEBUGGING
+    import time
+    import functools
+    import inspect
+    import logging
+    import os
+    import urllib.request
+    import urllib.parse
+
+    try:
+        from flask import has_request_context, g
+    except Exception:
+        def has_request_context():
+            return False
+        g = None
+
+    TRACE_THRESHOLD = float(os.environ.get("CHEM_TRACE_THRESHOLD", "0.0"))
+
+    chemtrace_logger = logging.getLogger("chemtrace")
+    if not chemtrace_logger.handlers:
+        chemtrace_logger.setLevel(logging.INFO)
+
+    def _short(x, n=200):
+        s = repr(x)
+        return s if len(s) <= n else s[:n-3] + "..."
+
+    def _find_app_caller():
+        for frame in inspect.stack()[2:]:
+            fn = frame.filename.replace("\\", "/")
+            if (
+                "site-packages" not in fn
+                and "/lib/python" not in fn
+                and not fn.endswith("/logging/__init__.py")
+            ):
+                return {
+                    "file": os.path.basename(frame.filename),
+                    "func": frame.function,
+                    "line": frame.lineno,
+                }
+        return None
+
+    def _url_info(url):
+        if not url:
+            return None
+        try:
+            parts = urllib.parse.urlsplit(str(url))
+            base = f"{parts.scheme}://{parts.netloc}" if parts.scheme and parts.netloc else None
+            return {
+                "url": str(url),
+                "base": base,
+                "host": parts.netloc or None,
+                "path": parts.path or "",
+            }
+        except Exception:
+            return {"url": _short(url), "base": None, "host": None, "path": None}
+
+    def _append_trace_event(event):
+        if has_request_context():
+            if getattr(g, "chem_trace", None) is None:
+                g.chem_trace = []
+            g.chem_trace.append(event)
+
+            info = event.get("target")
+            base = info.get("base") if isinstance(info, dict) else None
+            if base:
+                if getattr(g, "chem_bases", None) is None:
+                    g.chem_bases = []
+                g.chem_bases.append(base)
+        else:
+            chemtrace_logger.info("%r", event)
+
+    def trace_call(fn):
+        @functools.wraps(fn)
+        def wrapper(*args, **kwargs):
+            t0 = time.perf_counter()
+            ok = False
+            err = None
+            try:
+                result = fn(*args, **kwargs)
+                ok = True
+                return result
+            except Exception as e:
+                err = f"{type(e).__name__}: {e}"
+                raise
+            finally:
+                dt = time.perf_counter() - t0
+                if dt >= TRACE_THRESHOLD:
+                    _append_trace_event({
+                        "kind": "app",
+                        "fn": fn.__name__,
+                        "secs": round(dt, 4),
+                        "arg0": _short(args[0]) if args else None,
+                        "ok": ok,
+                        "err": err,
+                    })
+        return wrapper
+
+    def trace_external(label, fn, formatter=None):
+        @functools.wraps(fn)
+        def wrapper(*args, **kwargs):
+            t0 = time.perf_counter()
+            ok = False
+            err = None
+            caller = _find_app_caller()
+            target = None
+            if formatter is not None:
+                try:
+                    target = formatter(args, kwargs)
+                except Exception:
+                    target = None
+            try:
+                result = fn(*args, **kwargs)
+                ok = True
+                return result
+            except Exception as e:
+                err = f"{type(e).__name__}: {e}"
+                raise
+            finally:
+                dt = time.perf_counter() - t0
+                if dt >= TRACE_THRESHOLD:
+                    _append_trace_event({
+                        "kind": "remote",
+                        "fn": label,
+                        "caller": caller,
+                        "target": target,
+                        "secs": round(dt, 4),
+                        "ok": ok,
+                        "err": err,
+                    })
+        return wrapper
+
+    def _fmt_urlopen(args, kwargs):
+        url = args[0] if len(args) > 0 else kwargs.get("url")
+        info = _url_info(url)
+        if info is not None:
+            info["timeout"] = kwargs.get("timeout")
+        return info
+
+    def _fmt_requests(args, kwargs):
+        method = args[1] if len(args) > 1 else kwargs.get("method")
+        url = args[2] if len(args) > 2 else kwargs.get("url")
+        info = _url_info(url)
+        if info is not None:
+            info["method"] = method
+            info["timeout"] = kwargs.get("timeout")
+        return info
+
+    def _fmt_selenium_get(args, kwargs):
+        url = args[1] if len(args) > 1 else kwargs.get("url")
+        return _url_info(url)
+
+    def _fmt_pcp(args, kwargs):
+        query = args[0] if len(args) > 0 else kwargs.get("identifier")
+        namespace = args[1] if len(args) > 1 else kwargs.get("namespace")
+        info = _url_info(getattr(pcp, "API_BASE", None)) or {}
+        info.update({
+            "query": _short(query),
+            "namespace": namespace,
+        })
+        return info
+
+    def _fmt_cirpy(args, kwargs):
+        query = args[0] if len(args) > 0 else None
+        resolver = args[1] if len(args) > 1 else kwargs.get("resolver")
+        info = _url_info(getattr(cirpy, "API_BASE", None)) or {}
+        info.update({
+            "query": _short(query),
+            "resolver": resolver,
+        })
+        return info
+
 ORGANIC_ATOM_SET = {5, 6, 7, 8, 9, 15, 16, 17, 35, 53}
 METAL_ATOM_SET = set([3,4,11,12,13] + list(range(19,31+1)) + list(range(37,50+1)) + list(range(55,84+1)) + list(range(87,114+1)) + [116])
 with open('data/ceramics_list.txt', 'r') as fp:
@@ -317,7 +489,7 @@ def smiles2name(smiles):
         try:
             compounds = pcp.get_substances(smiles, namespace='smiles')
             # sometimes there are multiple substances, and multiple synonyms per substance
-            allsyns = [syn for c in compounds for syn in c.iupac_name if cas not in syn]
+            allsyns = [syn for c in compounds for syn in c.iupac_name if smiles not in syn]
             # choose the most common synonym
             fd = nltk.FreqDist(allsyns)
             name = fd.most_common(1)[0][0]
@@ -442,7 +614,7 @@ def name2iupac(string):
         try:
             compounds = pcp.get_substances(string, namespace='name')
             # sometimes there are multiple substances, and multiple synonyms per substance
-            allsyns = [syn for c in compounds for syn in c.synonyms if cas not in syn]
+            allsyns = [syn for c in compounds for syn in c.synonyms if string not in syn]
             # choose the most common synonym
             fd = nltk.FreqDist(allsyns)
             name = fd.most_common(1)[0][0]
@@ -586,7 +758,7 @@ def string2density(name):
     if is_cas(name):
         mask = df_pred['CASRN'] == name
         if sum(mask):
-            rho = float(df_pred[mask]['DENSITY_G/CM^3_TEST_PRED'])
+            rho = float(df_pred[mask]['DENSITY_G/CM^3_TEST_PRED'].iloc[0])
             rho_origin = 'comptox/pred'
     # try to scrape from PubChem
     if pd.isna(rho):
@@ -1167,3 +1339,38 @@ def getLogP(cas,mol):
         LogP_origin = 'rdkit/calc'
     return LogP, LogP_origin
 
+### DEBUGGING
+if 1:
+    ResolveChemical = trace_call(ResolveChemical)
+    smiles2name = trace_call(smiles2name)
+    cas2smiles = trace_call(cas2smiles)
+    cas2name = trace_call(cas2name)
+    name2iupac = trace_call(name2iupac)
+    name2cas = trace_call(name2cas)
+    name2smiles = trace_call(name2smiles)
+    string2density = trace_call(string2density)
+    string2mp = trace_call(string2mp)
+    mol2mp = trace_call(mol2mp)
+    if hasattr(pcp, "urlopen"):
+        pcp.urlopen = trace_external("pubchempy.urlopen", pcp.urlopen, _fmt_urlopen)
+
+    if hasattr(cirpy, "urlopen"):
+        cirpy.urlopen = trace_external("cirpy.urlopen", cirpy.urlopen, _fmt_urlopen)
+
+    pcp.get_compounds = trace_external("pcp.get_compounds", pcp.get_compounds, _fmt_pcp)
+    pcp.get_substances = trace_external("pcp.get_substances", pcp.get_substances, _fmt_pcp)
+    cirpy.resolve = trace_external("cirpy.resolve", cirpy.resolve, _fmt_cirpy)
+    urllib.request.urlopen = trace_external("urllib.request.urlopen", urllib.request.urlopen, _fmt_urlopen)
+    requests.sessions.Session.request = trace_external(
+        "requests.Session.request",
+        requests.sessions.Session.request,
+        _fmt_requests,
+    )
+
+    if try_dsstox:
+        selenium.webdriver.Chrome.get = trace_external(
+            "selenium.webdriver.Chrome.get",
+            selenium.webdriver.Chrome.get,
+            _fmt_selenium_get,
+        )
+

color2_module/templates/chemError.html

@@ -16,9 +16,11 @@
 <div style="font-size:5rem;text-align:center"> &#129318; </div>
 
 <p style="font-size:2rem;text-align:center">
-    Uh-oh! Something went wrong. We were unable to match your chemical.  Please return to the previous page and try a
-    different identifier.
+    Uh-oh! Something went wrong. We were unable to automatically identify your chemical.  Please return to the previous page and try a
+    different identifier. You may try to manually determine the SMILES structural code for your chemical using tools like 
+    <a href='https://cactus.nci.nih.gov/chemical/structure'>NCI/CADD Chemical Identifier Resolver</a>, <a href='https://pubchem.ncbi.nlm.nih.gov/'>PubChem</a>, or
+    <a href='https://webbook.nist.gov/chemistry/'>NIST Chemistry WebBook</a>. 
 </p>
 
 
-</body>
+</body>

color3_module/templates/chemError.html

@@ -16,9 +16,11 @@
 <div style="font-size:5rem;text-align:center"> &#129318; </div>
 
 <p style="font-size:2rem;text-align:center">
-    Uh-oh! Something went wrong. We were unable to match your chemical.  Please return to the previous page and try a
-    different identifier.
+    Uh-oh! Something went wrong. We were unable to automatically identify your chemical.  Please return to the previous page and try a
+    different identifier. You may try to manually determine the SMILES structural code for your chemical using tools like 
+    <a href='https://cactus.nci.nih.gov/chemical/structure'>NCI/CADD Chemical Identifier Resolver</a>, <a href='https://pubchem.ncbi.nlm.nih.gov/'>PubChem</a>, or
+    <a href='https://webbook.nist.gov/chemistry/'>NIST Chemistry WebBook</a>. 
 </p>
 
 
-</body>
+</body>

exposure2_module/templates/exposure2_chemError.html

@@ -16,8 +16,10 @@
 <div style="font-size:5rem;text-align:center"> &#129318; </div>
 
 <p style="font-size:2rem;text-align:center">
-    Uh-oh! Something went wrong. We were unable to match your chemical.  Please return to the previous page and try a
-    different identifier.
+    Uh-oh! Something went wrong. We were unable to automatically identify your chemical.  Please return to the previous page and try a
+    different identifier. You may try to manually determine the SMILES structural code for your chemical using tools like 
+    <a href='https://cactus.nci.nih.gov/chemical/structure'>NCI/CADD Chemical Identifier Resolver</a>, <a href='https://pubchem.ncbi.nlm.nih.gov/'>PubChem</a>, or
+    <a href='https://webbook.nist.gov/chemistry/'>NIST Chemistry WebBook</a>. 
 </p>
 
 

exposure3_module/exposure.py

@@ -14,7 +14,7 @@ from rdkit.Chem import AllChem as Chem
 # get additional physical properties, options are: logp, rho, mp
 #get_properties = [] # don't get any; this breaks ceramics logic
 #get_properties = ['logp','rho','mp'] # get all three
-get_properties = ['mp'] # only get mp
+get_properties = ['mp', 'rho']  
 # show additional physical properties
 show_properties = False
 # output additional info for physical properties

exposure3_module/templates/exposure3_chemError.html

@@ -16,8 +16,10 @@
 <div style="font-size:5rem;text-align:center"> &#129318; </div>
 
 <p style="font-size:2rem;text-align:center">
-    Uh-oh! Something went wrong. We were unable to match your chemical.  Please return to the previous page and try a
-    different identifier.
+    Uh-oh! Something went wrong. We were unable to automatically identify your chemical.  Please return to the previous page and try a
+    different identifier. You may try to manually determine the SMILES structural code for your chemical using tools like 
+    <a href='https://cactus.nci.nih.gov/chemical/structure'>NCI/CADD Chemical Identifier Resolver</a>, <a href='https://pubchem.ncbi.nlm.nih.gov/'>PubChem</a>, or
+    <a href='https://webbook.nist.gov/chemistry/'>NIST Chemistry WebBook</a>. 
 </p>
 
 

exposure_module/templates/chemError.html

@@ -16,9 +16,11 @@
 <div style="font-size:5rem;text-align:center"> &#129318; </div>
 
 <p style="font-size:2rem;text-align:center">
-    Uh-oh! Something went wrong. We were unable to match your chemical.  Please return to the previous page and try a
-    different identifier.
+    Uh-oh! Something went wrong. We were unable to automatically identify your chemical.  Please return to the previous page and try a
+    different identifier. You may try to manually determine the SMILES structural code for your chemical using tools like 
+    <a href='https://cactus.nci.nih.gov/chemical/structure'>NCI/CADD Chemical Identifier Resolver</a>, <a href='https://pubchem.ncbi.nlm.nih.gov/'>PubChem</a>, or
+    <a href='https://webbook.nist.gov/chemistry/'>NIST Chemistry WebBook</a>. 
 </p>
 
 
-</body>
+</body>

quantity_module/templates/quantity_chemError.html

@@ -16,8 +16,10 @@
 <div style="font-size:5rem;text-align:center"> &#129318; </div>
 
 <p style="font-size:2rem;text-align:center">
-    Uh-oh! Something went wrong. We were unable to match your chemical.  Please return to the previous page and try a
-    different identifier.
+    Uh-oh! Something went wrong. We were unable to automatically identify your chemical.  Please return to the previous page and try a
+    different identifier. You may try to manually determine the SMILES structural code for your chemical using tools like 
+    <a href='https://cactus.nci.nih.gov/chemical/structure'>NCI/CADD Chemical Identifier Resolver</a>, <a href='https://pubchem.ncbi.nlm.nih.gov/'>PubChem</a>, or
+    <a href='https://webbook.nist.gov/chemistry/'>NIST Chemistry WebBook</a>. 
 </p>