def parse_sig_points():
p=Parser("/AIP/ENR/ENR 4/ES_ENR_4_4_en.pdf")
points=[]
for pagenr in xrange(p.get_num_pages()):
#print "Processing page %d"%(pagenr,)
page=p.parse_page_to_items(pagenr)
lines=page.get_lines(page.get_all_items(),order_fudge=20)
for line in lines:
cols=line.split()
if len(cols)>2:
coordstr=" ".join(cols[1:3])
#print cols
if len(mapper.parsecoords(coordstr))>0:
crd=mapper.parsecoord(coordstr)
#print "Found %s: %s"%(cols[0],crd)
points.append(dict(
name=cols[0],
kind='sig. point',
pos=crd))
p=Parser("/AIP/ENR/ENR 4/ES_ENR_4_1_en.pdf")
for pagenr in xrange(p.get_num_pages()):
page=p.parse_page_to_items(pagenr)
nameheading,=page.get_by_regex(r".*Name of station.*")
freqheading,=page.get_by_regex(r".*Frequency.*")
coordheading,=page.get_by_regex(r".*Coordinates.*")
items=sorted(list(x for x in page.get_partially_in_rect(nameheading.x1,nameheading.y2+2,nameheading.x1+1,100) if x.text.strip()),key=lambda x:x.y1)
idx=0
while True:
if items[idx].text.strip()=="":
idx+=1
continue
if idx+1>=len(items):
break
name=items[idx]
kind=items[idx+1]
diffy=kind.y1-name.y2
#print "Name, kind:",name,kind
#print name.text,kind.text,diffy
assert kind.text.count("VOR") or kind.text.count("DME") or kind.text.count("NDB")
assert diffy<0.5
#print "Frq cnt: <%s>"%(page.get_partially_in_rect(freqheading.x1,name.y1+0.05,freqheading.x2,kind.y2-0.05),)
freqraw=" ".join(page.get_lines(page.get_partially_in_rect(freqheading.x1,name.y1+0.05,freqheading.x2,kind.y2-0.05)))
short,freq=re.match(r"\s*([A-Z]{2,3})?\s*(\d+(?:\.?\d+)\s+(?:MHz|kHz))\s*(?:H24)?\s*",freqraw).groups()
posraw=" ".join(page.get_lines(page.get_partially_in_rect(coordheading.x1,name.y1+0.05,coordheading.x2,kind.y2-0.05)))
#print "Rawpos<%s>"%(posraw,)
pos=mapper.parse_coords(*re.match(r".*?(\d+\.\d+[NS]).*?(\d+\.\d+[EW]).*",posraw).groups())
#print "Name: %s, Shortname: %s, Freq: %s,pos: %s"%(name.text,short,freq,pos)
points.append(dict(
name=short+" "+kind.text.strip()+" "+name.text.strip(),
short=short,
kind="nav-aid",
pos=pos,
freq=freq))
idx+=2
return points
def ey_parse_airfield(icao):
spaces = []
p = Parser("/EY_AD_2_%s_en.pdf" % (icao, ), lambda x: x)
freqs = []
for nr in xrange(0, p.get_num_pages()):
page = p.parse_page_to_items(nr)
if nr == 0:
#[–-]
nameregex = ur"\s*%s\s*[–-]\s*(.*?)\s*$" % (icao, )
print "Nameregex", nameregex
nameitem = page.get_by_regex(nameregex, re.UNICODE)[0]
name, = re.match(nameregex, nameitem.text, re.UNICODE).groups()
name = name.replace("Tarptautinis", "International")
#print repr(name)
#sys.exit(1)
coordhdg, = page.get_by_regex(ur".*ARP\s*koordinat.s.*", re.DOTALL)
coord = page.get_partially_in_rect(coordhdg.x2 + 4,
coordhdg.y1 + 0.1, 100,
coordhdg.y2 - 0.1)[0]
pos, = mapper.parsecoords(fixup(coord.text.replace(" ", "")))
elevhdg, = page.get_by_regex(ur".*Vietos\s*aukštis.*", re.DOTALL)
elevitem, = page.get_partially_in_rect(elevhdg.x2 + 1,
elevhdg.y1 + 0.1, 100,
elevhdg.y2 - 0.1)
elev, = re.match(ur"(\d+)\s*FT.*", elevitem.text).groups()
elev = int(elev)
for comm in page.get_by_regex(ur".*ATS\s*COMMUNICATION\s*FACILITIES.*",
re.DOTALL):
ends = page.get_by_regex_in_rect(ur".*RADIO\s*NAVIGATION.*", 0,
comm.y2, 100, 100)
if ends:
end = ends[0].y1 - 0.1
else:
end = 100
freqitems = page.get_by_regex_in_rect(ur".*\d{3}\.\d{3}.*", 0,
comm.y2, 100, end - 0.1)
lastservice = None
for freq in freqitems:
service = page.get_partially_in_rect(0, freq.y1 + 0.1, 17,
freq.y2 - 0.1)
if service:
lastservice = service[0]
print lastservice
assert len(spaces) == 0
for freqstr in re.findall(ur"\d{3}\.\d{3}", freq.text):
if freqstr != "121.500" and freqstr != "243.000":
freqs.append(
(lastservice.text.split("/")[0], float(freqstr)))
def ey_parse_airfield(icao):
spaces=[]
p=Parser("/EY_AD_2_%s_en.pdf"%(icao,),lambda x:x)
freqs=[]
for nr in xrange(0,p.get_num_pages()):
page=p.parse_page_to_items(nr)
if nr==0:
#[–-]
nameregex=ur"\s*%s\s*[–-]\s*(.*?)\s*$"%(icao,)
print "Nameregex",nameregex
nameitem=page.get_by_regex(nameregex,re.UNICODE)[0]
name,=re.match(nameregex,nameitem.text,re.UNICODE).groups()
name=name.replace("Tarptautinis","International")
#print repr(name)
#sys.exit(1)
coordhdg,=page.get_by_regex(ur".*ARP\s*koordinat.s.*",re.DOTALL)
coord=page.get_partially_in_rect(
coordhdg.x2+4,coordhdg.y1+0.1,100,coordhdg.y2-0.1)[0]
pos,=mapper.parsecoords(fixup(coord.text.replace(" ","")))
elevhdg,=page.get_by_regex(ur".*Vietos\s*aukštis.*",re.DOTALL)
elevitem,=page.get_partially_in_rect(
elevhdg.x2+1,elevhdg.y1+0.1,100,elevhdg.y2-0.1)
elev,=re.match(ur"(\d+)\s*FT.*",elevitem.text).groups()
elev=int(elev)
for comm in page.get_by_regex(ur".*ATS\s*COMMUNICATION\s*FACILITIES.*",re.DOTALL):
ends=page.get_by_regex_in_rect(
ur".*RADIO\s*NAVIGATION.*",
0,comm.y2,100,100)
if ends:
end=ends[0].y1-0.1
else:
end=100
freqitems=page.get_by_regex_in_rect(
ur".*\d{3}\.\d{3}.*",
0,comm.y2,100,end-0.1)
lastservice=None
for freq in freqitems:
service=page.get_partially_in_rect(
0,freq.y1+0.1,17,freq.y2-0.1)
if service:
lastservice=service[0]
print lastservice
assert len(spaces)==0
for freqstr in re.findall(ur"\d{3}\.\d{3}",freq.text):
if freqstr!="121.500" and freqstr!="243.000":
freqs.append((lastservice.text.split("/")[0],float(freqstr)))
def fi_parse_airfield(icao=None):
spaces=[]
ad=dict()
assert icao!=None
ad['icao']=icao
sigpoints=[]
#https://ais.fi/ais/eaip/pdf/aerodromes/EF_AD_2_EFET_EN.pdf
#https://ais.fi/ais/eaip/aipcharts/efet/EF_AD_2_EFET_VAC.pdf
#vacp=parse.Parser("/ais/eaip/aipcharts/%s/EF_AD_2_%s_VAC.pdf"%(icao.lower(),icao),lambda x: x,country="fi")
def remove_italics(x):
return x.replace("<i>","").replace("</i>","")
p=parse.Parser("/ais/eaip/pdf/aerodromes/EF_AD_2_%s_EN.pdf"%(icao,),remove_italics,country="fi")
#The following doesn't actually work, since finnish VAC are bitmaps!!! :-(
if 0:
vacpage=vacp.parse_page_to_items(0)
repp=vacpage.get_by_regex("\s*REPORTING\s*POINTS\s*")
assert len(repp)>0
for item in repp:
lines=iter(page.get_lines(page.get_partially_in_rect(item.x1,item.y2+0.1,100,100)))
for line in lines:
uprint("Looking for reporting points:%s"%(line,))
name,lat,lon=re.match(ur"([A-ZÅÄÖ\s ]{3,})\s*([ \d]+N)\s*([ \d]+E).*",line)
sigpoints.append(dict(
name=icao+" "+name.strip(),
kind="reporting",
pos=mapper.parse_coords(lat.replace(" ",""),lon.replace(" ",""))))
page=p.parse_page_to_items(0)
nameregex=ur"%s\s+-\s+([A-ZÅÄÖ\- ]{3,})"%(icao,)
for item in page.get_by_regex(nameregex):
#print "fontsize:",item.fontsize
assert item.fontsize>=14
ad['name']=re.match(nameregex,item.text).groups()[0].strip()
break
for item in page.get_by_regex(ur".*ELEV\s*/\s*REF.*"):
lines=page.get_lines(page.get_partially_in_rect(0,item.y1+0.1,100,item.y2-0.1))
for line in lines:
print "Line:",line
ft,=re.match(".*ELEV.*([\d\.]+)\s*FT.*",line).groups()
assert not 'elev' in ad
ad['elev']=float(ft)
for item in page.get_by_regex(ur"Mittapisteen.*sijainti"):
lines=page.get_lines(page.get_partially_in_rect(item.x1,item.y1,100,item.y2))
for line in lines:
for crd in mapper.parsecoords(line):
assert not ('pos' in ad)
ad['pos']=crd
parse_landing_chart.help_plc(ad,
"/ais/eaip/aipcharts/%s/EF_AD_2_%s_ADC.pdf"%(icao.lower(),icao.upper()),
icao,ad['pos'],country='fi'
)
parse_landing_chart.help_plc(ad,
"/ais/eaip/aipcharts/%s/EF_AD_2_%s_VAC.pdf"%(icao.lower(),icao.upper()),
icao,ad['pos'],country='fi',variant='VAC'
)
parse_landing_chart.help_plc(ad,
"/ais/eaip/aipcharts/%s/EF_AD_2_%s_LDG.pdf"%(icao.lower(),icao.upper()),
icao,ad['pos'],country='fi',variant='landing'
)
parse_landing_chart.help_plc(ad,
"/ais/eaip/aipcharts/%s/EF_AD_2_%s_APDC.pdf"%(icao.lower(),icao.upper()),
icao,ad['pos'],country='fi',variant='parking'
)
aip_text_documents.help_parse_doc(ad,"/ais/eaip/pdf/aerodromes/EF_AD_2_%s_EN.pdf"%(icao.upper(),),
icao,"fi",title="General Information",category="general")
ad['runways']=[]
thrs=[]
freqs=[]
for pagenr in xrange(p.get_num_pages()):
page=p.parse_page_to_items(pagenr)
if page==None: continue
for item in page.get_by_regex("\s*RUNWAY\s*PHYSICAL\s*CHARACTERISTICS\s*"):
lines=page.get_lines(page.get_partially_in_rect(0,item.y2+0.1,100,100))
for line in lines:
if re.match(ur"AD\s+2.13",line): break
m=re.match(ur".*?(RWY END)?\s*\*?(\d{6}\.\d+N)\s*(\d{6,7}\.\d+E).*",line)
if not m:continue
rwyend,lat,lon=m.groups()
rwytxts=page.get_lines(page.get_partially_in_rect(0,line.y1,12,line.y2))
print "Rwytxts:",rwytxts
rwytxt,=rwytxts
uprint("rwytext:",rwytxt)
rwy,=re.match(ur"\s*(\d{2}[LRCM]?)\s*[\d.]*\s*",rwytxt).groups()
have_thr=False
for thr in thrs:
if thr['thr']==rwy:
have_thr=True
if rwyend!=None and have_thr:
continue
thrs.append(dict(pos=mapper.parse_coords(lat,lon),thr=rwy))
for item in page.get_by_regex("ATS AIRSPACE"):
lines=iter(page.get_lines(page.get_partially_in_rect(0,item.y2+0.1,100,100)))
spaces=[]
line=lines.next()
while True:
while line.strip()=="":
line=lines.next()
print "Read line:",line
if line.count("Vertical limits"):
break
m=re.match(ur".*?/\s+Designation and lateral limits\s*(.*\b(?:CTR|FIZ)\b.*?)\s*:?\s*$",line)
if not m:
m=re.match(ur"\s*(.*\b(?:CTR|FIZ)\b.*?)\s*:",line)
#print "Second try:",m
spacename,=m.groups()
#print "Got spacename:",spacename
assert spacename.strip()!=""
coords=[]
while True:
line=lines.next()
print "Further:",line
if line.count("Vertical limits"):
print "Breaking"
break
if not re.search(ur"[\d ]+N\s*[\d ]+E",line) and \
not re.search(ur"circle|cent[red]{1,5}|pitkin|point|equal\s*to",line):
print "Breaking"
break
coords.append(line)
areaspec="".join(coords)
def fixup(m):
lat,lon=m.groups()
return lat.replace(" ","")+" "+lon.replace(" ","")
areaspec=re.sub(ur"([\d ]+N)\s*([\d ]+E)",fixup,areaspec)
areaspec=re.sub(ur"\(.*/\s*equal\s*to\s*Malmi\s*CTR\s*lateral\s*limits\)","",areaspec)
#print "Fixed areaspec",areaspec
#if icao=="EFKS":
# areaspec=areaspec.replace("6615 28N","661528N")
#Error! REstriction areas!
spaces.append(dict(
name=spacename,
type="CTR",
points=mapper.parse_coord_str(areaspec)))
if line.count("Vertical limits"):
#print "Breaking"
break
while not line.count("Vertical limits"):
line=lines.next()
#print "Matching veritcal limits--------------------------------"
oldspaces=spaces
spaces=[]
for space in oldspaces:
if space['name'].count("/"):
a,b=space['name'].split("/")
spaces.append(dict(space,name=a.strip()))
spaces.append(dict(space,name=b.strip()))
else:
spaces.append(space)
missing=set([space['name'] for space in spaces])
while True:
for space in spaces:
for it in xrange(3):
cand=space['name']
if it==1:
if cand.count("CTR"):
cand="CTR"
if cand.count("FIZ"):
cand="FIZ"
if it==2:
if cand.count("CTR"):
cand=r"CTR\s*/[\sA-Z]+"
if cand.count("FIZ UPPER"):
cand="FIZ UPPER"
if cand.count("FIZ LOWER"):
cand="FIZ LOWER"
m=re.match(ur".*%s\s*:([^,:-]*)\s*-\s*([^,:-]*)"%(cand,),line)
print "Matching ",cand," to ",line,"missing:",missing,m
if m: break
if len(spaces)==1 and not m:
m=re.match(ur".*Vertical limits\s*(.*)\s*-\s*(.*)",line)
if m:
print "*****MATCH!!:::",m.groups()
for lim in m.groups():
assert lim.count(",")==0
space['floor'],space['ceiling']=m.groups()
missing.remove(space['name'])
#print "Missing:"
if len(missing)==0: break
if len(missing)==0: break
#print "Still missing:",missing
line=lines.next()
print "Parse f o n page",pagenr
for item2 in page.get_by_regex(ur".*ATS\s*COMMUNICATION\s*FACILITIES.*"):
lines=page.get_lines(page.get_partially_in_rect(0,item2.y2+0.1,100,100))
for line in lines:
if line.count("RADIO NAVIGATION AND LANDING AIDS"): break
print "Comm line:",line
twr=re.match(ur"TWR.*(\d{3}\.\d{3})\b.*",line)
if twr:
freqs.append(('TWR',float(twr.groups()[0])))
atis=re.match(ur"ATIS.*(\d{3}\.\d{3})",line)
if atis:
freqs.append(('ATIS',float(atis.groups()[0])))
def ev_parse_airfields():
ads=[]
spaces=[]
seen=set()
cur_airac=get_cur_airac()
assert cur_airac
for icao in ["EVRA",
"EVLA",
"EVTJ",
"EVVA"]:
thrs=[]
url="/eAIPfiles/%s-AIRAC/html/eAIP/EV-AD-2.%s-en-GB.html"%(cur_airac,icao)
data,date=fetchdata.getdata(url,country='ev')
parser=lxml.html.HTMLParser()
parser.feed(data)
tree=parser.close()
elev=None
pos=None
ctrarea=None
ctr=None
ctralt=None
ctrname=None
adcharturl=None
adchart=None
adnametag,=tree.xpath("//p[@class='ADName']")
adnamestr=alltext(adnametag)
print adnamestr
name,=re.match(ur"%s\s*[-—]\s*([\w\s]+)"%(icao,),adnamestr,re.UNICODE).groups()
freqs=[]
for table in tree.xpath("//table"):
rows=list(table.xpath(".//tr"))
headings=list(table.xpath(".//th"))
if len(headings)==5:
if headings[2]=="Frequency":
for row in rows:
cols=alltexts(table.xpath(".//td"))
desig,name=cols[0:2]
freq,=re.match(ur"\d{3}\.\d{3}\s*MHz",cols[2]).groups()
if freq!="121.500":
freqs.append((desig+" "+name,float(freq)))
continue
for row in rows:
cols=alltexts(row.xpath(".//td"))
print "cols:",repr(cols)
if len(cols)<2: continue
if not pos and re.match(ur".*ARP\s*coordinates.*",cols[1]):
pos,=mapper.parsecoords(cols[2])
if not elev and re.match(ur"Elevation.*",cols[1]):
elev,=re.match(ur"(\d+) FT.*",cols[2]).groups()
if not ctr and re.match(ur"Designation\s*and\s*lateral\s*limits",cols[1]):
lines=cols[2].split("\n")
ctr=True
print "Got lateral limits",lines[0]
try:
ctrname,type_=re.match(ur"^([\w\s]+)(CTR|TIZ)",lines[0]).groups()
ctrarea=" ".join(lines[1:])
except:
ctrname,type_=re.match(ur"^([\w\s]+)(CTR|TIZ)",lines[0]+lines[1]).groups()
ctrarea=" ".join(lines[2:])
assert ctrname.strip()
ctrname=ctrname.strip()+" "+type_
#print ".",cols[1],"."
if not ctralt and re.match(ur".*Vertical\s*limits.*",cols[1],re.UNICODE):
ctralt=True
#print "<",cols[2],">"
alts=cols[2].split("/")
if len(alts)==1:
ceiling=alts[0]
floor="GND"
else:
ceiling,floor=alts
print "Parsed",ceiling,floor
def parse_sig_points():
p = Parser("/AIP/ENR/ENR 4/ES_ENR_4_4_en.pdf")
points = []
for pagenr in xrange(p.get_num_pages()):
#print "Processing page %d"%(pagenr,)
page = p.parse_page_to_items(pagenr)
lines = page.get_lines(page.get_all_items(), order_fudge=20)
for line in lines:
cols = line.split()
if len(cols) > 2:
coordstr = " ".join(cols[1:3])
#print cols
if len(mapper.parsecoords(coordstr)) > 0:
crd = mapper.parsecoord(coordstr)
#print "Found %s: %s"%(cols[0],crd)
points.append(
dict(name=cols[0], kind='sig. point', pos=crd))
p = Parser("/AIP/ENR/ENR 4/ES_ENR_4_1_en.pdf")
for pagenr in xrange(p.get_num_pages()):
page = p.parse_page_to_items(pagenr)
nameheading, = page.get_by_regex(r".*Name of station.*")
freqheading, = page.get_by_regex(r".*Frequency.*")
coordheading, = page.get_by_regex(r".*Coordinates.*")
items = sorted(list(x for x in page.get_partially_in_rect(
nameheading.x1, nameheading.y2 + 2, nameheading.x1 + 1, 100)
if x.text.strip()),
key=lambda x: x.y1)
idx = 0
while True:
if items[idx].text.strip() == "":
idx += 1
continue
if idx + 1 >= len(items):
break
name = items[idx]
kind = items[idx + 1]
diffy = kind.y1 - name.y2
#print "Name, kind:",name,kind
#print name.text,kind.text,diffy
assert kind.text.count("VOR") or kind.text.count(
"DME") or kind.text.count("NDB")
assert diffy < 0.5
#print "Frq cnt: <%s>"%(page.get_partially_in_rect(freqheading.x1,name.y1+0.05,freqheading.x2,kind.y2-0.05),)
freqraw = " ".join(
page.get_lines(
page.get_partially_in_rect(freqheading.x1, name.y1 + 0.05,
freqheading.x2,
kind.y2 - 0.05)))
short, freq = re.match(
r"\s*([A-Z]{2,3})?\s*(\d+(?:\.?\d+)\s+(?:MHz|kHz))\s*(?:H24)?\s*",
freqraw).groups()
posraw = " ".join(
page.get_lines(
page.get_partially_in_rect(coordheading.x1, name.y1 + 0.05,
coordheading.x2,
kind.y2 - 0.05)))
#print "Rawpos<%s>"%(posraw,)
pos = mapper.parse_coords(*re.match(
r".*?(\d+\.\d+[NS]).*?(\d+\.\d+[EW]).*", posraw).groups())
#print "Name: %s, Shortname: %s, Freq: %s,pos: %s"%(name.text,short,freq,pos)
points.append(
dict(name=short + " " + kind.text.strip() + " " +
name.text.strip(),
short=short,
kind="nav-aid",
pos=pos,
freq=freq))
idx += 2
return points
ad['name'] = re.match(nameregex, item.text).groups()[0].strip()
break
for item in page.get_by_regex(ur".*ELEV\s*/\s*REF.*"):
lines = page.get_lines(
page.get_partially_in_rect(0, item.y1 + 0.1, 100, item.y2 - 0.1))
for line in lines:
print "Line:", line
ft, = re.match(".*ELEV.*([\d\.]+)\s*FT.*", line).groups()
assert not 'elev' in ad
ad['elev'] = float(ft)
for item in page.get_by_regex(ur"Mittapisteen.*sijainti"):
lines = page.get_lines(
page.get_partially_in_rect(item.x1, item.y1, 100, item.y2))
for line in lines:
for crd in mapper.parsecoords(line):
assert not ('pos' in ad)
ad['pos'] = crd
parse_landing_chart.help_plc(ad,
"/ais/eaip/aipcharts/%s/EF_AD_2_%s_ADC.pdf" %
(icao.lower(), icao.upper()),
icao,
ad['pos'],
country='fi')
parse_landing_chart.help_plc(ad,
"/ais/eaip/aipcharts/%s/EF_AD_2_%s_VAC.pdf" %
(icao.lower(), icao.upper()),
icao,
ad['pos'],
country='fi',
def ee_parse_airfield(icao=None):
spaces = []
ad = dict()
ad["icao"] = icao
sigpoints = []
p = parse.Parser("/ee_%s.pdf" % (icao,), lambda x: x, country="ee")
page = p.parse_page_to_items(0)
print icao
nameregex = ur".*%s\s*[-−]\s*([A-ZÅÄÖ\- ]{3,})" % (icao,)
for item in page.get_by_regex(nameregex):
print "fontsize:", item.fontsize
assert item.fontsize >= 10
ad["name"] = re.match(nameregex, item.text).groups()[0].strip()
break
else:
raise Exception("Found no airfield name!")
for item in page.get_by_regex(ur".*Kõrgus merepinnast.*"):
lines = page.get_lines(page.get_partially_in_rect(0, item.y1 + 0.1, 100, item.y2 - 0.1))
for line in lines:
ft, = re.match(".*?([\d\.]+)\s*FT\.*", line).groups()
assert not "elev" in ad
print "parsed ft:", ft
ad["elev"] = float(ft)
for item in page.get_by_regex(ur"ARP koordinaadid"):
lines = page.get_lines(page.get_partially_in_rect(item.x1, item.y1, 100, item.y2))
for line in lines:
print line
for crd in mapper.parsecoords(line):
assert not ("pos" in ad)
ad["pos"] = crd
break
else:
raise Exception("No coords")
ad["runways"] = []
thrs = []
freqs = []
for pagenr in xrange(p.get_num_pages()):
page = p.parse_page_to_items(pagenr)
print "Parsing page", pagenr
for item in page.get_by_regex("\s*RUNWAY\s*PHYSICAL\s*CHARACTERISTICS\s*"):
print "Phys char"
coords, = page.get_by_regex_in_rect("RWY end coordinates", 0, item.y2, 100, 100)
design, = page.get_by_regex_in_rect("Designations", 0, item.y2, 100, 100)
lines = page.get_lines(page.get_partially_in_rect(0, design.y2, design.x2, 100))
print "Design", lines
rwys = []
for line in lines:
m = re.match("(\d{2})", line)
if m:
print "rwynum", line
rwys.append((m.groups()[0], line.y1))
rwys.append((None, 100))
for (rwy, y), (nextrwy, nexty) in izip(rwys, rwys[1:]):
lines = page.get_lines(page.get_partially_in_rect(coords.x1, y, coords.x2, nexty - 0.5))
lines = [line for line in lines if line.strip()]
print "Lines for rwy", lines
thrlat, thrlon, endlat, endlon, undulation = lines[:5]
assert undulation.count("GUND")
thrs.append(dict(pos=mapper.parse_coords(thrlat, thrlon), thr=rwy))
print thrs
if 0:
for item in page.get_by_regex("ATS AIRSPACE"):
lines = iter(page.get_lines(page.get_partially_in_rect(0, item.y2 + 0.1, 100, 100)))
spaces = []
while True:
line = lines.next()
# print "Read line:",line
if line.count("Vertical limits"):
break
m = re.match(ur".*?/\s+Designation and lateral limits\s*(.*\b(?:CTR|FIZ)\b.*?)\s*:?\s*$", line)
if not m:
m = re.match(ur"\s*(.*\b(?:CTR|FIZ)\b.*?)\s*:", line)
# print "Second try:",m
spacename, = m.groups()
# print "Got spacename:",spacename
assert spacename.strip() != ""
coords = []
while True:
line = lines.next()
# print "Further:",line
if line.count("Vertical limits"):
break
if not re.search(ur"[\d ]+N\s*[\d ]+E", line) and not re.search(
ur"circle|cent[red]{1,5}|pitkin|point", line
):
break
coords.append(line)
areaspec = "".join(coords)
def fixup(m):
lat, lon = m.groups()
return lat.replace(" ", "") + " " + lon.replace(" ", "")
areaspec = re.sub(ur"([\d ]+N)\s*([\d ]+E)", fixup, areaspec)
# print "Fixed areaspec",areaspec
# if icao=="EFKS":
# areaspec=areaspec.replace("6615 28N","661528N")
# Error! REstriction areas!
spaces.append(dict(name=spacename, type="CTR", points=mapper.parse_coord_str(areaspec)))
if line.count("Vertical limits"):
# print "Breaking"
break
while not line.count("Vertical limits"):
line = lines.next()
# print "Matching veritcal limits--------------------------------"
oldspaces = spaces
spaces = []
for space in oldspaces:
if space["name"].count("/"):
a, b = space["name"].split("/")
spaces.append(dict(space, name=a.strip()))
spaces.append(dict(space, name=b.strip()))
else:
spaces.append(space)
missing = set([space["name"] for space in spaces])
while True:
for space in spaces:
# print "Matching ",space['name']," to ",line,"missing:",missing
for it in xrange(2):
cand = space["name"]
if it == 1:
if cand.count("CTR"):
cand = "CTR"
if cand.count("FIZ"):
cand = "FIZ"
m = re.match(ur".*%s\s*:([^,:-]*)\s*-\s*([^,:-]*)" % (cand,), line)
if m:
break
if len(spaces) == 1 and not m:
m = re.match(ur".*Vertical limits\s*(.*)\s*-\s*(.*)", line)
if m:
for lim in m.groups():
assert lim.count(",") == 0
space["floor"], space["ceiling"] = m.groups()
missing.remove(space["name"])
# print "Missing:"
if len(missing) == 0:
break
if len(missing) == 0:
break
line = lines.next()
print "Parse f o n page", pagenr
for item2 in page.get_by_regex(ur".*ATS\s*COMMUNICATION\s*FACILITIES.*"):
lines = page.get_lines(page.get_partially_in_rect(0, item2.y2 + 0.1, 100, 100))
for line in lines:
if line.count("RADIO NAVIGATION AND LANDING AIDS"):
break
print "Comm line:", line
twr = re.match(ur"TWR.*(\d{3}\.\d{3})\b.*", line)
if twr:
freqs.append(("TWR", float(twr.groups()[0])))
atis = re.match(ur"ATIS.*(\d{3}\.\d{3})", line)
if atis:
freqs.append(("ATIS", float(atis.groups()[0])))
