def getdefisandtrefis():
displayedgraph = graph.Graph()
displayedfiles = graph.add_omgroup_data(mathhub_dir, root_repo, root_doc, displayedgraph, ONLY_COVERED_PART)
displayedfiles += displayedgraph.module_nodes
logger = harvest.SimpleLogger(2)
ctx = harvest.HarvestContext(logger, harvest.DataGatherer(), mathhub_dir)
newfiles = displayedfiles[:]
while newfiles:
for filename in newfiles:
if not os.path.isfile(filename):
print("File " + filename + " doesn't exist")
continue
ctx.repo = harvest.split_path_repo_doc(filename)[1]
ctx.gatherer.push_repo(ctx.repo, ctx)
root, name = os.path.split(filename)
harvest.harvest_file(root, name, ctx)
newfiles = []
for inp in ctx.gatherer.mhinputrefs:
destfile = inp["dest_path"]
if destfile not in displayedfiles:
newfiles.append(destfile)
displayedfiles.append(destfile)
return (ctx.gatherer.defis, ctx.gatherer.trefis)
def getdefisandtrefis():
displayedgraph = graph.Graph()
displayedfiles = graph.add_omgroup_data(mathhub_dir, root_repo, root_doc,
displayedgraph, ONLY_COVERED_PART)
displayedfiles += displayedgraph.module_nodes
logger = harvest.SimpleLogger(2)
ctx = harvest.HarvestContext(logger, harvest.DataGatherer(), mathhub_dir)
newfiles = displayedfiles[:]
while newfiles:
for filename in newfiles:
if not os.path.isfile(filename):
print("File " + filename + " doesn't exist")
continue
ctx.repo = os.path.join(mathhub_dir,
harvest.split_path_repo_doc(filename)[0])
ctx.gatherer.push_repo(ctx.repo, ctx)
root, name = os.path.split(filename)
harvest.harvest_file(root, name, ctx)
newfiles = []
fringe = [m["dest_path"] for m in ctx.gatherer.mhinputrefs]
if BIG:
fringe += [m["dest_path"] for m in ctx.gatherer.importmhmodules]
# both signature and language bindings?
fringe += [
os.path.join(mathhub_dir, m["dest_repo"], "source",
m["dest_mod"] + "." + args.LANGUAGE + ".tex")
for m in ctx.gatherer.gimports
]
fringe += [
os.path.join(mathhub_dir, m["dest_repo"], "source",
m["dest_mod"] + ".tex")
for m in ctx.gatherer.gimports
]
for destfile in fringe:
if destfile not in displayedfiles:
newfiles.append(destfile)
displayedfiles.append(destfile)
return (ctx.gatherer.defis, ctx.gatherer.trefis)
"--verbosity",
type=int,
default=1,
choices=range(4),
help="the verbosity (default: 1)")
parser.add_argument(
"DIRECTORY",
nargs="+",
help=
"git repo or higher level directory for which statistics are generated"
)
args = parser.parse_args()
if args.verbosity >= 2:
print("GATHERING DATA\n")
logger = harvest.SimpleLogger(args.verbosity)
# determine mathhub folder
mathhub_repo = os.path.abspath(args.DIRECTORY[0])
while not mathhub_repo.endswith("MathHub"):
new = os.path.split(mathhub_repo)[0]
if new == mathhub_repo:
raise Exception("Failed to infer MathHub directory")
mathhub_repo = new
for directory in args.DIRECTORY:
if not os.path.isdir(os.path.join(
directory, ".git")): ## TODO: Is there a better way?
raise Exception("'" + directory +
"' doesn't appear to be a git repository")
parser.add_argument("-e", "--emacs", action="store_true")
parser.add_argument(
"DIRECTORY",
nargs="+",
help="git repo or higher level directory which is debugged")
args = parser.parse_args()
verbosity = args.verbosity
if args.emacs:
import datetime
emacs_bufferpath = "/tmp/lmh_debug-" + str(
datetime.datetime.now()).replace(" ", "T") + ".log"
logger = EmacsLogger(verbosity, emacs_bufferpath)
else:
logger = harvest.SimpleLogger(verbosity)
logger.log("GATHERING DATA\n", minverbosity=2)
mathhub_dir = harvest.get_mathhub_dir(args.DIRECTORY[0])
ctx = harvest.HarvestContext(logger, harvest.DataGatherer(), mathhub_dir)
for directory in args.DIRECTORY:
harvest.gather_data_for_all_repos(directory, ctx)
logger.log("\n\nCHECKING DATA\n", minverbosity=2)
check_data(ctx.gatherer, verbosity, logger)
if args.incomplete_mhmodnl:
logger.log("\n\nLOOKING FOR MISSING VERBALIZATIONS IN MHMODNLs\n",
minverbosity=2)
check_mvx(ctx.gatherer, logger)
return ("\\begin{smentry}{" + keystr + "}{" + self.repo + "}" + "\n" +
usestr + "\n" + self.defstr.strip() + "\n" +
"\\end{smentry}\n")
if __name__ == "__main__":
import argparse
parser = argparse.ArgumentParser(
description="Script for creating a glossary from e.g. smglom")
parser.add_argument("LANGUAGE", help="language of the glossary (e.g. en)")
parser.add_argument(
"DIRECTORY",
nargs="+",
help=
"git repo or higher level directory from which the glossary is generated"
)
args = parser.parse_args()
mathhub_dir = harvest.get_mathhub_dir(args.DIRECTORY[0])
lang = args.LANGUAGE
logger = harvest.SimpleLogger(0) # for now: 0 verbosity
ctx = harvest.HarvestContext(logger, harvest.DataGatherer(), mathhub_dir)
for directory in args.DIRECTORY:
harvest.gather_data_for_all_repos(directory, ctx)
glossary = Glossary(lang, mathhub_dir)
glossary.fill(ctx.gatherer)
print(glossary)
import lmh_harvest as harvest
import sys
PATH = sys.argv[1]
VERBOSITY = 1
gatherer = harvest.DataGatherer()
logger = harvest.SimpleLogger(VERBOSITY)
harvest.gather_data_for_all_repos(PATH,
harvest.HarvestContext(logger, gatherer))
for symi in gatherer.symis:
if "gfc" in symi["params"]:
print("I found a symi with gfc:")
print(" ", symi)
for defi in gatherer.defis:
if "gfa" in defi["params"]:
print("I found a defi with gfa:")
print(" ", defi)
for m in ctx.gatherer.gimports
]
for destfile in fringe:
if destfile not in displayedfiles:
newfiles.append(destfile)
displayedfiles.append(destfile)
return (ctx.gatherer.defis, ctx.gatherer.trefis)
defis, trefis = getdefisandtrefis()
# Now we need to gather everything imported to find definitions for trefis
logger = harvest.SimpleLogger(2)
mygraph = graph.Graph()
graph.fill_graph(mathhub_dir, root_repo, root_doc, mygraph, ONLY_COVERED_PART)
ctx = harvest.HarvestContext(logger, harvest.DataGatherer(), mathhub_dir)
relevantfiles = \
list(mygraph.g_nodes.keys()) +\
list(mygraph.module_nodes.keys()) +\
[k[0] for k in mygraph.omgroup_nodes.keys()]
extrafiles = []
for filename in relevantfiles:
# check computer.en.tex if computer.tex is used
lf = filename[:-4] + "." + args.LANGUAGE + ".tex"
"""
Very experimental tool to generate a GF (Grammatical Framework) Lexicon from SMGloM
"""
import lmh_harvest as harvest
import sys
directories = sys.argv[1:]
mathhub_dir = harvest.get_mathhub_dir(directories[0])
ctx = harvest.HarvestContext(harvest.SimpleLogger(2), harvest.DataGatherer(),
mathhub_dir)
for directory in directories:
harvest.gather_data_for_all_repos(directory, ctx)
symi_dict = {}
for symi in ctx.gatherer.symis:
symb = symi["mod_name"].replace("-", "_") + "_" + symi["name"].replace(
"-", "_")
if "gfc" in symi["params"]:
symi_dict[symb] = symi["params"]["gfc"]
def umlautSubst(s):
return s.replace("\"a", "ä")\
.replace("\"o", "ö")\
.replace("\"u", "ü")\
.replace("\"A", "Ä")\
.replace("\"O", "Ö")\
.replace("\"U", "Ü")\
.replace("\"s", "ß")
def fill_graph(mathhub, root_repo, root_doc, graph, onlycovered = False):
potential_modules = add_omgroup_data(mathhub, root_repo, root_doc, graph, onlycovered)
blocked_nodes = potential_modules[:]
logger = harvest.SimpleLogger(2)
potential_nodes = {}
potential_edges = []
gimports = []
while potential_modules:
gatherer = harvest.DataGatherer()
context = harvest.HarvestContext(logger, gatherer, mathhub)
for pm in potential_modules:
context.repo = "/".join(pm.split("/")[:mathhub.count("/")+3]) # TODO: platform independence
path = pm
root, filename = os.path.split(path)
try:
harvest.harvest_file(root, filename, context)
except FileNotFoundError:
print("couldn't find '" + path + "'")
for mod in gatherer.modules:
node = mod["path"]
if node not in potential_nodes.keys():
name = mod["mod_name"]
if not name:
name = os.path.split(node)[1][:-4]
potential_nodes[node] = {"label" : name, "type" : "module"}
for mod in gatherer.langfiles:
node = mod["path"]
if node not in potential_nodes.keys():
name = mod["mod_name"]
if not name:
name = os.path.split(node)[1][:-4]
potential_nodes[node] = {"label" : name, "type" : "langfile"}
for file_ in gatherer.textfiles:
node = file_["path"]
if node not in potential_nodes.keys():
potential_nodes[node] = {"label" : os.path.split(node)[1], "type" : "text"}
assert not gatherer.sigfiles
potential_modules = [] # includes text files
for inp in gatherer.mhinputrefs:
destnode = inp["dest_path"]
if destnode not in blocked_nodes:
blocked_nodes.append(destnode)
potential_modules.append(destnode)
potential_edges.append((inp["path"], destnode))
for imp in gatherer.importmhmodules:
gimports.append((imp["path"], imp["dest_path"]))
graph.g_edges[gimports[-1]] = {"type":{"importmhmodule":"import","usemhmodule":"use"}[imp["type"]]}
for gimport in gatherer.gimports:
gimports.append((gimport["path"],
os.path.join(gimport["dest_repo"], "source", gimport["dest_mod"]) + ".tex"))
graph.g_edges[gimports[-1]] = {"type":{"gimport":"import","guse":"use"}[gimport["type"]]}
for node in potential_nodes.keys():
graph.module_nodes[node] = {
"label" : potential_nodes[node]["label"],
"type" : potential_nodes[node]["type"],
}
for start, end in potential_edges:
if start in potential_nodes.keys() and end in potential_nodes.keys():
graph.module_edges[(start, end)] = {}
## handle gimports
assert graph.g_nodes == {}
while gimports:
gatherer = harvest.DataGatherer()
context = harvest.HarvestContext(logger, gatherer, mathhub)
for source, dest in gimports:
if dest not in graph.g_nodes.keys() and dest not in potential_nodes.keys():
context.repo = "/".join(dest.split("/")[:mathhub.count("/")+3]) # TODO: platform independence
root, filename = os.path.split(dest)
try:
harvest.harvest_file(root, filename, context)
except FileNotFoundError:
print("couldn't find '" + dest + "'")
assert not gatherer.langfiles
assert not gatherer.textfiles
for mod in gatherer.modules + gatherer.sigfiles:
node = mod["path"]
if node not in potential_nodes.keys() and node not in graph.g_nodes.keys():
name = mod["mod_name"]
if not name:
name = os.path.split(node)[1][:-4]
graph.g_nodes[node] = {"label" : name, "type" : "module"}
gimports = []
for gimport in gatherer.gimports:
pair = (gimport["path"], os.path.join(gimport["dest_repo"], "source", gimport["dest_mod"]) + ".tex")
graph.g_edges[pair] = {"type":{"gimport":"import","guse":"use"}[gimport["type"]]}
if pair[1] not in graph.g_nodes.keys() and pair[1] not in potential_nodes.keys():
gimports.append(pair)
for imp in gatherer.importmhmodules:
pair = (imp["path"], imp["dest_path"])
graph.g_edges[pair] = {"type":{"importmhmodule":"import","usemhmodule":"use"}[imp["type"]]}
if pair[1] not in graph.g_nodes.keys() and pair[1] not in potential_nodes.keys():
gimports.append(pair)