Have filter-regs emit a special value "-COMPUTED-" for filtered data values,
rather than blanking them out entirely. This lets csv-to-json.py handle the case where an earlier input file has (e.g.) a registration value which does not match the computed value, and then a later input file has a value that does match. In this case we want to override the older value with the newer value, then notice that the registration can be omitted when writing the database. Previously in this case the older (incorrect) value would be used.
This commit is contained in:
parent
0d2bd6ae34
commit
35299c47ba
|
@ -37,6 +37,16 @@ def readcsv(name, infile, blocks):
|
||||||
|
|
||||||
print >>sys.stderr, 'Read', ac_count, 'aircraft from', name
|
print >>sys.stderr, 'Read', ac_count, 'aircraft from', name
|
||||||
|
|
||||||
|
def cleandb(blocks):
|
||||||
|
for blockdata in blocks.values():
|
||||||
|
for dkey in list(blockdata.keys()):
|
||||||
|
block = blockdata[dkey]
|
||||||
|
for key in list(block.keys()):
|
||||||
|
if block[key] == '-COMPUTED-':
|
||||||
|
del block[key]
|
||||||
|
if len(block) == 0:
|
||||||
|
del blockdata[dkey]
|
||||||
|
|
||||||
def writedb(blocks, todir, blocklimit, debug):
|
def writedb(blocks, todir, blocklimit, debug):
|
||||||
block_count = 0
|
block_count = 0
|
||||||
|
|
||||||
|
@ -110,5 +120,6 @@ if __name__ == '__main__':
|
||||||
with closing(open(filename, 'r')) as infile:
|
with closing(open(filename, 'r')) as infile:
|
||||||
readcsv(filename, infile, blocks)
|
readcsv(filename, infile, blocks)
|
||||||
|
|
||||||
|
cleandb(blocks)
|
||||||
writedb(blocks, sys.argv[-1], 2500, False)
|
writedb(blocks, sys.argv[-1], 2500, False)
|
||||||
sys.exit(0)
|
sys.exit(0)
|
||||||
|
|
|
@ -3,10 +3,16 @@
|
||||||
// ICAO addresses (column 'icao24') and registrations
|
// ICAO addresses (column 'icao24') and registrations
|
||||||
// (column 'r')
|
// (column 'r')
|
||||||
//
|
//
|
||||||
// It removes all registration entries that exactly match
|
// It replaces all registration entries that exactly match
|
||||||
// what dump1090 would have computed from the hexid anyway,
|
// what dump1090 would have computed from the hexid anyway
|
||||||
// reducing the size of the CSV in the cases where the
|
// with the special value "-COMPUTED-"; these values are
|
||||||
// two approaches match.
|
// removed from the final data when csv-to-json.py writes
|
||||||
|
// the json database, reducing the size of the database
|
||||||
|
// in the cases where the two approaches match.
|
||||||
|
//
|
||||||
|
// It does a similar transformation on 'desc' (aircraft type
|
||||||
|
// description) and 'wtc' (wake turbulence categogy) based
|
||||||
|
// on the aircraft type designator in 't', if provided.
|
||||||
//
|
//
|
||||||
// Any additional columns are passed through unchanged.
|
// Any additional columns are passed through unchanged.
|
||||||
//
|
//
|
||||||
|
@ -28,7 +34,7 @@ var transformer = csv.transform(function (record, callback) {
|
||||||
if ('r' in record && record.r != '') {
|
if ('r' in record && record.r != '') {
|
||||||
var computed = reglookup(record.icao24);
|
var computed = reglookup(record.icao24);
|
||||||
if (computed === record.r) {
|
if (computed === record.r) {
|
||||||
record.r = '';
|
record.r = '-COMPUTED-';
|
||||||
} else if (computed !== null) {
|
} else if (computed !== null) {
|
||||||
console.warn(record.icao24 + " computed registration " + computed + " but CSV data had " + record.r);
|
console.warn(record.icao24 + " computed registration " + computed + " but CSV data had " + record.r);
|
||||||
}
|
}
|
||||||
|
@ -38,7 +44,7 @@ var transformer = csv.transform(function (record, callback) {
|
||||||
if ('desc' in record && record.desc != '') {
|
if ('desc' in record && record.desc != '') {
|
||||||
var computed_desc = actypes[record.t].desc;
|
var computed_desc = actypes[record.t].desc;
|
||||||
if (computed_desc === record.desc) {
|
if (computed_desc === record.desc) {
|
||||||
record.desc = '';
|
record.desc = '-COMPUTED-';
|
||||||
} else if (computed_desc !== undefined) {
|
} else if (computed_desc !== undefined) {
|
||||||
// too noisy, the icao descriptors are very coarse and reality often disagrees
|
// too noisy, the icao descriptors are very coarse and reality often disagrees
|
||||||
//console.warn(record.icao24 + " (" + record.t + "): computed type description " + computed_desc + " but CSV data had " + record.desc);
|
//console.warn(record.icao24 + " (" + record.t + "): computed type description " + computed_desc + " but CSV data had " + record.desc);
|
||||||
|
@ -48,7 +54,7 @@ var transformer = csv.transform(function (record, callback) {
|
||||||
if ('wtc' in record && record.wtc != '') {
|
if ('wtc' in record && record.wtc != '') {
|
||||||
var computed_wtc = actypes[record.t].wtc;
|
var computed_wtc = actypes[record.t].wtc;
|
||||||
if (computed_wtc === record.wtc) {
|
if (computed_wtc === record.wtc) {
|
||||||
record.wtc = '';
|
record.wtc = '-COMPUTED-';
|
||||||
} else if (computed_desc !== undefined) {
|
} else if (computed_desc !== undefined) {
|
||||||
//console.warn(record.icao24 + " (" + record.t + "): computed type WTC " + computed_wtc + " but CSV data had " + record.wtc);
|
//console.warn(record.icao24 + " (" + record.t + "): computed type WTC " + computed_wtc + " but CSV data had " + record.wtc);
|
||||||
}
|
}
|
||||||
|
|
Loading…
Reference in a new issue