diff --git a/doc/get-marcxml-inspire b/doc/get-marcxml-inspire --- a/doc/get-marcxml-inspire +++ b/doc/get-marcxml-inspire @@ -1,16 +1,16 @@ #! /usr/bin/env bash for EXPT in alice atlas cms lhcb star cleo h1 zeus babar belle; do - for YEAR in $(seq 2010 $(date +"%Y")); do + for YEAR in $(seq 1980 $(date +"%Y")); do OUT=inspire-$EXPT-$YEAR.marc.xml if [[ -e $OUT ]]; then echo "$OUT exists: skipping $EXPT $YEAR download" else echo "Downloading $EXPT $YEAR Inspire record to $OUT" #URL="https://cds.cern.ch/search?ln=en&cc=${COLL}&op1=a&m1=a&p1=${YEAR}&f1=year&rg=200&jrec=1&of=xm" URL="https://inspirehep.net/search?ln=en&ln=en&p=find+cn+${EXPT}+and+ac+100%2B+and+de+${YEAR}&of=xm&action_search=Search&sf=earliestdate&so=d&rm=&rg=250&sc=0&ot=001,024,035,037,710,245" echo "$URL" wget "$URL" -O $OUT fi done done diff --git a/doc/mk-coverage-html b/doc/mk-coverage-html --- a/doc/mk-coverage-html +++ b/doc/mk-coverage-html @@ -1,395 +1,403 @@ #! /usr/bin/env python from __future__ import division, print_function """\ %prog [ ...] TODO: - do Rivet lookup in this script, not the JSON-maker - get and write year of publication in table """ import argparse ap = argparse.ArgumentParser(usage=__doc__) ap.add_argument("JSONFILES", metavar="file", nargs="+", help="JSON Inspire xref file to read") ap.add_argument("-r", "--ranking", dest="RANKFILES", metavar="file", action="append", default=[], help="lists of Inspire IDs to exclude, suppress, and highlight") ap.add_argument("-R", "--reverse", dest="REVERSE", action="store_true", default=False, help="show list *reverse* ordered in Inspire ID") ap.add_argument("-s", "--only-searches", dest="ONLYSEARCHES", action="store_true", default=False, help="only show search analyses") ap.add_argument("-S", "--no-searches", dest="NOSEARCHES", action="store_true", default=False, help="exclude search analyses") ap.add_argument("-i", "--only-heavyion", dest="ONLYHEAVYION", action="store_true", default=False, help="only show heavy ion analyses") ap.add_argument("-I", "--no-heavyion", dest="NOHEAVYION", action="store_true", default=False, help="exclude heavy ion analyses") ap.add_argument("-o", "--outfile", dest="OUTFILE", default=None, help="output HTML filename") ap.add_argument("--basename", dest="BASENAME", default="rivet-coverage", help="the base name for output files [default=%(default)s]") ap.add_argument("--update-ranking", dest="UPDATERANK", action="store_true", default=False, help="update the per-experiment ranking files") ap.add_argument("-v", "--verbose", dest="VERBOSE", action="store_true", default=False, help="print debug info to the terminal") args = ap.parse_args() import datetime now = datetime.datetime.now() -EXPTS = ["ALICE", "ATLAS", "CMS", "LHCb", "Other"] - +## Experiment (grouping) names and regex patterns +import re +EXPTS = ["ALICE", "ATLAS", "CMS", "LHCb", "B-factories", "HERA", "Other"] +EXPT_PATTS = ["ALICE", "ATLAS", "CMS", "LHCb", "BABAR|BELLE", "H1|ZEUS"] +EXPT_REOBJS = [re.compile(patt, re.I) for patt in EXPT_PATTS] ## Add the rivet Python module build dir(s) to the Python module path, then import -import os, sys, re +import os, sys pybuild = os.path.abspath(os.path.join(os.getcwd(), "..", "pyext", "build")) pydirs = [os.path.join(pybuild, d) for d in os.listdir(pybuild) if re.match(r"lib\..*-.*-%d\.%d" % (sys.version_info[0], sys.version_info[1]), d)] sys.path = pydirs + sys.path import rivet ## Add info file locations from glob import glob dirpatt = os.path.join(os.getcwd(), "..", "analyses", "plugin*") for d in glob(dirpatt): #print(d) rivet.addAnalysisDataPath(os.path.abspath(d)) ## Rivet analyses to cross-reference ranas = {} for aname in rivet.AnalysisLoader.analysisNames(): ana = rivet.AnalysisLoader.getAnalysis(aname) # TODO: all anas *should* have an Inspire ID... try: # print(aname, ":", ana.inspireId(), ":") ranas.setdefault(int(ana.inspireId()), []).append(ana.name()) except: pass ## Read data from JSON files records = {} import json for jsonfile in args.JSONFILES: with open(jsonfile) as jf: recs = json.load(jf) if args.VERBOSE: print("Reading {} records from {}".format(len(recs), jsonfile)) records.update(recs) records = {int(k) : v for k, v in records.items()} if args.VERBOSE: print("Read total of {} records".format(len(records))) ## Read Inspire IDs from ranking files blacklist, greylist, hotlist = [], [], [] assigned = {} for rankfilestr in args.RANKFILES: for rankfile in rankfilestr.split(" "): with open(rankfile) as rf: if args.VERBOSE: print("Reading rankings from {}".format(rankfile)) for line in rf: line = line.strip() if not line or line.startswith("#"): continue tokens = line.split() ins = int(tokens[0]) code = tokens[1] if code == "X": blacklist.append(ins) elif code == "?": greylist.append(ins) elif code == "!": hotlist.append(ins) # Detect an optional assigned email address last = tokens[-1] if "@" in last: if last.startswith("<") and last.endswith(">"): last = last[1:-1] assigned[ins] = last ## Add rankings/tags to the record for ins, rec in records.items(): ## Sanitise title and experiment rec[0] = (rec[0] or "[NO TITLE]").replace("\n", " ") rec[1] = (rec[1] or "UNKNOWN").upper().split()[0].strip() ## Ranking code = "default" if ins in ranas: code = "rivet" elif ins in greylist: code = "grey" elif ins in blacklist: code = "black" elif ins in hotlist: code = "hot" ## Tags import re title = rec[0] or "" if "search" in title.lower(): code += " search" - if any(re.search(x, title) is not None for x in ["Pb", "Xe", "lead[ ,$]", "heavy[- ]ion"]): + if any(re.search(x, title) is not None for x in ["Pb", "Xe", "Au", "U+U", "gold", "lead[ ,$]", "heavy[- ]ion"]): code += " heavyion" rm = False rm |= args.ONLYSEARCHES and not "search" in code rm |= args.NOSEARCHES and "search" in code rm |= args.ONLYHEAVYION and not "heavyion" in code rm |= args.NOHEAVYION and "heavyion" in code if rm: del records[ins] else: rec.append(code) ## Group and count records by experiment (and update rank file if requested) ex_records = {} ex_ntots, ex_ndefaults, ex_nurgents, ex_nwanteds, ex_ntargets, ex_nrivets = {}, {}, {}, {}, {}, {} -for ex in EXPTS: +for iex, ex in enumerate(EXPTS): + + ## Name matching if ex != "Other": - ex_records[ex] = {ins : rec for ins, rec in records.items() if rec[1].upper() == ex.upper()} + ex_records[ex] = {ins : rec for ins, rec in records.items() + if EXPT_REOBJS[iex].match(rec[1])} else: - namedexpts = [e.upper() for e in EXPTS[:-1]] - ex_records[ex] = {ins : rec for ins, rec in records.items() if rec[1].upper() not in namedexpts} + ex_records[ex] = {ins : rec for ins, rec in records.items() + if not any(reobj.match(rec[1]) for reobj in EXPT_REOBJS)} + + ## Count matches ex_ntots[ex] = len(ex_records[ex]) ex_nrivets[ex] = len([ins for ins, rec in ex_records[ex].items() if "rivet" in rec[-1]]) ex_ndefaults[ex] = len([ins for ins, rec in ex_records[ex].items() if "default" in rec[-1]]) ex_nurgents[ex] = len([ins for ins, rec in ex_records[ex].items() if "hot" in rec[-1]]) ex_nwanteds[ex] = ex_ndefaults[ex] + ex_nurgents[ex] ex_ntargets[ex] = ex_nwanteds[ex] + ex_nrivets[ex] if args.VERBOSE: print(ex, "#urgent/#wanted =", ex_nurgents[ex], "/", ex_nwanteds[ex]) if args.UPDATERANK: if args.ONLYSEARCHES or args.NOSEARCHES or args.ONLYHEAVYION or args.NOHEAVYION: print("Won't update rank lists while search/HI/experiment filtering is enabled") sys.exit(1) rfname = "{}-{}.rank".format(args.BASENAME, ex.lower()) print("Writing updated rank file to {}".format(rfname)) syms = { "default" : ".", "rivet" : ".", "grey" : "?", "black" : "X", "hot" : "!" } with open(rfname, "w") as rf: for ins, rec in sorted(ex_records[ex].items()): rankcode = rec[-1].split()[0] # line = u"{} {} {}\n".format(ins.encode("UTF-8"), syms[code], rec[3].encode("UTF-8")) line = u"{} {} {}".format(ins, syms[rankcode], rec[0]) # print(assigned.get(ins)) if ins in assigned: #print(ins, rec[0], assigned[ins]) line += " <{}>".format(assigned[ins]) line += "\n" rf.write(line.encode("UTF-8")) ntot = len(records) nrivet = len([ins for ins, rec in records.items() if "rivet" in rec[-1]]) ndefault = len([ins for ins, rec in records.items() if "default" in rec[-1]]) nurgent = len([ins for ins, rec in records.items() if "hot" in rec[-1]]) nwanted = ndefault + nurgent ntarget = nwanted + nrivet ## Register filter strings excls = [] if args.ONLYSEARCHES: excls.append("searches only") if args.NOSEARCHES: excls.append("no searches") if args.ONLYHEAVYION: excls.append("heavy ion only") if args.NOHEAVYION: excls.append("no heavy ion") ## Web page rendering import html OUT = html.HTML("html") -title = "Rivet LHC analysis coverage" +title = "Rivet analysis coverage" exclstr = " ({})".format(", ".join(excls)) if excls else "" title += exclstr head = OUT.head(newlines=True) head.meta(charset="utf-8") head.title(title) head.link("", rel="stylesheet", href="https://code.jquery.com/ui/1.12.1/themes/base/jquery-ui.css") head.script("MathJax.Hub.Config({ tex2jax: {inlineMath: [['$','$']]} });", type="text/x-mathjax-config") head.script("", type="text/javascript", src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.4/MathJax.js?config=TeX-MML-AM_CHTML", async="async") head.script("", type="text/javascript", src="https://code.jquery.com/jquery-3.3.1.js", integrity="sha256-2Kok7MbOyxpgUVvAk/HJ2jigOSYS2auK4Pfzbm7uH60=", crossorigin="anonymous") head.script("", type="text/javascript", src="https://code.jquery.com/ui/1.12.1/jquery-ui.js", integrity="sha256-T0Vest3yCU7pafRw9r+settMBX6JkKN06dqBnpQ8d30=", crossorigin="anonymous") head.script(""" $(document).ready( function(){ $("#blacktoggle").click( function(){ var b = $("#blacktoggle"); var t = b.text(); b.text(t.indexOf("Show") != -1 ? t.replace("Show", "Hide") : t.replace("Hide", "Show") ); $(".black").toggle(100); }); $("#greytoggle").click( function(){ var b = $("#greytoggle"); var t = b.text(); b.text(t.indexOf("Show") != -1 ? t.replace("Show", "Hide") : t.replace("Hide", "Show") ); $(".grey").toggle(100); }); $("#tabs").tabs(); }); """) style = head.style(newlines="True") style += "html { font-family: sans; font-size: large; color: #333; }" style += "body { padding: 2em; }" style += "table { margin: 2em 0 2em 0; border: 0; border-collapse: collapse; text-align: left; }" style += "table.list { border-top: 3px solid black; border-bottom: 3px solid black; }" style += "table.list thead { border-bottom: 1px solid #333; }" style += "table.key { border: 1px solid #333; margin: 0; }" style += "td { padding: 15px; }" style += "tr.ana { border-top: 1px solid #ccc; }" style += "tr.ana td { padding-bottom: 1em; padding-top: 1em; }" style += "a { color: #339; }" style += "button { margin: 1em; }" # style += ".row { margin: 1em 0 3em 0; }" # style += ".row:after { content: ''; display: table; clear: both; }" # style += ".col { float: left; width: 50%; }" style += "button { border: none; margin: 0 1em 1em 0; border-radius: 1ex; color: #333; background: #ddf; padding: 1ex; }" style += "button:hover { background: #cce; }" style += "button:active { color: white; }" style += "#tabs { border: 0; }" style += ".rivet { background: #cfc; }" style += ".hot { background: #fbb; }" style += ".default { background: #fee; }" style += ".grey { color: #666; background: #ddd; font-size: normal; display: none; }" style += ".grey a { color: #669; }" style += ".black { color: #eee; background: #333; display: none; }" style += ".black a { color: #99c; }" style += ".hot.assigned { background: repeating-linear-gradient(135deg, #fbb, #fbb 10px, #bd7 10px, #bd7 20px); }" style += ".default.assigned { background: repeating-linear-gradient(135deg, #fee, #fee 10px, #de9 10px, #de9 20px); }" style += ".grey.assigned { background: repeating-linear-gradient(135deg, #ddd, #ddd 10px, #dfd 10px, #dfd 20px); }" body = OUT.html.body(newlines=True) body.h1(title) body.p().b("Rivet analyses exist for {}/{} papers = {:.0f}%. {} priority analyses required.".format(nrivet, ntarget, 100*nrivet/ntarget, nurgent)) body.p("Total number of Inspire papers scanned = {}, at {}".format(ntot, now.strftime("%Y-%m-%d"))) body.p("Breakdown by identified experiment (in development):") t = body.table(klass="list") th = t.thead(newlines=True) r = th.tr(klass="thead") r.td().b("Key") for ex in EXPTS: r.td().b(ex) # tb = t.tbody(newlines=True) r = tb.tr(klass="default") r.td().b("Rivet wanted (total):") for ex in EXPTS: r.td("{}".format(ex_nwanteds[ex])) # r = tb.tr(klass="hot") r.td().b("Rivet REALLY wanted:") for ex in EXPTS: r.td("{}".format(ex_nurgents[ex])) r = tb.tr(klass="rivet") # r.td().b("Rivet provided:") for ex in EXPTS: # txt = "{}".format(ex_nrivets[ex]) # if ex_ntargets[ex]: # txt += " / {:d} = {:.0f}%".format(ex_ntargets[ex], 100*ex_nrivets[ex]/ex_ntargets[ex]) # r.td(txt) b = r.td().b("{}".format(ex_nrivets[ex])) if ex_ntargets[ex]: b.span("/{:d} = ".format(ex_ntargets[ex]), style="color: #777") b += "{:.0f}%".format(100*ex_nrivets[ex]/ex_ntargets[ex]) body.button("Show greylist", id="greytoggle") body.button("Show blacklist", id="blacktoggle") #body.input(klass="search", placeholder="Search") #body.button("Sort by name", klass="sort", data-sort="name") tabs = body.div(id="tabs") u = tabs.ul() for ex in EXPTS: u.li().a(ex, href="#{}expt".format(ex.lower())) for ex in EXPTS: d = tabs.div(id="{}expt".format(ex.lower())) t = d.table(klass="list").tbody(newlines=True) for i, (ins, rec) in enumerate(sorted(ex_records[ex].items(), reverse=args.REVERSE)): expt = rec[1] code = rec[-1] if ins in assigned: code += " assigned" if expt: code += " {}expt".format(expt.lower()) cell = t.tr(klass=code+" ana", newlines=True).td(newlines=False) # Title summ = u"" summ += u"{}: {}".format(expt, rec[0]) cell.span().b(summ) ## Inspire ID and report numbers p = cell.p() p.span("Inspire ID: {} ".format(ins)) if rec[4]: p.span("arXiv ID: {} ".format(rec[4])) if rec[7]: p.span(u" Report IDs: " + u", ".join(rec[7])) ## Links p = cell.span("Links: ") ## Inspire p.a("Inspire", href="http://inspirehep.net/record/{}".format(ins)) # Inspire p += " " ## DOI if rec[2]: p.a("DOI/journal", href="http://dx.doi.org/{}".format(rec[2])) p += " " ## CDS if rec[3]: p.a("CDS", href="https://cds.cern.ch/record/{}".format(rec[3])) p += " " ## arXiv if rec[4]: p.a("arXiv", href="https://arxiv.org/abs/{}".format(rec[4])) p += " " ## HepData if rec[5]: p.a("HepData", href="https://hepdata.net/record/{}".format(rec[5])) p += " " ## Rivet if ins in ranas: anas = u", ".join(ranas[ins]) p += " " p.a(anas, href="https://rivet.hepforge.org/analyses/{}.html".format(ranas[ins][0])) ## In-progress/assignment if ins in assigned: p += " " p.a("IN PROGRESS: assigned to {}".format(assigned[ins]), href="mailto:{}".format(assigned[ins])) ## Time-created footer body.p("Generated at {}".format(now.strftime("%c"))) body.p("Generated from JSON files extracted from Inspire ({} papers in total):".format(ntot)) body.p(", ".join(args.JSONFILES), style="font-family: monospace; font-size: smaller") ## Write out outfile = args.OUTFILE if not outfile: outfile = args.BASENAME exclparts = [e.replace(" ", "") for e in excls] if exclparts: outfile += "-" + "-".join(exclparts) if not outfile.endswith(".html"): outfile += ".html" print("Writing output to {} {}".format(outfile, exclstr)) with open(outfile, "wb") as hf: a = unicode(OUT) hf.write(a.encode("UTF-8"))