bandsaunter/packaging/make-browse-man.py

#!/usr/bin/env python3
"""Generate the saunterbrowse manual page.

Hand-written rather than generated from a table: unlike the scanner, the
browser's surface is a dozen keys and five flags, and describing those is
prose, not a listing.  The version and date still come from the program, so
the page cannot claim to document a release that was never built.
"""
import sys
from datetime import date
from pathlib import Path

sys.path.insert(0, str(Path(__file__).resolve().parent.parent))

import bandsaunter                              # noqa: E402
from bandsaunter.browse import FILING, PLAYERS, SORTS   # noqa: E402


def _english(items) -> str:
    """a, b and c -- the way a sentence lists things."""
    items = list(items)
    if len(items) < 2:
        return "".join(items)
    return ", ".join(items[:-1]) + " and " + items[-1]


PAGE = r'''.\" Generated by packaging/make-browse-man.py -- do not edit by hand.
.TH SAUNTERBROWSE 1 "{date}" "bandsaunter {version}" "User Commands"
.SH NAME
saunterbrowse \- read and listen to what a bandsaunter scan collected
.SH SYNOPSIS
.B saunterbrowse
.RI [ DIRECTORY ]
.RB [ \-\-sort
.IR ORDER ]
.RB [ \-\-filter
.IR TEXT ]
.RB [ \-\-player
.IR CMD ]
.RB [ \-\-list ]
.RB [ \-\-callsigns ]
.RB [ \-\-kml
.RI [ FILE ]]
.RB [ \-\-no\-lookup ]
.SH DESCRIPTION
A scan leaves a directory of recordings. Beside each one is a JSON file
holding what the classifier made of it, and for speech a transcript of what
was said. Reading that by hand means opening files one at a time and guessing
which are worth playing.
.PP
.B saunterbrowse
shows them as a list you move through with the arrow keys. The transcript of
whichever recording is highlighted fills the top of the screen, because that
is the part you actually want to read; underneath it are the identification,
the bands the frequency falls in, and the list itself. Pressing Enter plays
the recording.
.PP
Each line of the list gives the frequency, the date and time, the mode, how
long it ran and what was said. The moment is written
.BR "YY-mm-dd hh:mm:ss am/pm" ,
date first so that a column of them reads down in order, and on a twelve-hour
clock so that it reads the way you would say it. The list starts in that
order, newest first.
.PP
With no
.I DIRECTORY
it opens the one the scanner writes to, taken from your saved settings, so it
normally needs no arguments at all.
.PP
Recordings can also be dealt with as they are read. A key files one into
{filing_dirs}, another deletes it outright, and another locks its frequency
out of every later scan. Nothing else is written: without one of those keys
the browser only reads.
.SH KEYS
.TP
.B "Up Down k j"
Move through the recordings.
.TP
.B "PgUp PgDn"
A screenful at a time.
.TP
.B "Home End"
The first and the last.
.TP
.B Enter
Play the highlighted recording. Playing a second one stops the first: two
players talking over each other is worse than either alone.
.TP
.B Space
Stop playing. With nothing playing, it starts, like Enter.
.TP
.B t
Read the whole transcript full screen, scrolling with the arrow keys. Useful
for a long net, where the panel at the top can only show the first few lines
\[em] it says so when there is more.
.TP
.B /
Filter. What you type is matched against the frequency, the filename, the
identification and
.I everything that was said,
so "was the repeater mentioned" is a question you can ask directly. Enter
accepts, Escape clears.
.TP
.B s
Cycle the order: {sorts}.
.TP
.B r
Re-read the directory. A scan running in another window is still writing to
it, and this picks up what has arrived since.
.TP
.B o
Print the highlighted recording's path and quit, for piping into something
else.
.TP
.B "{filing_keys}"
File the highlighted recording into {filing_list} respectively \[em] the
recording and every sidecar written beside it, together. See
.B MANAGING THE RECORDINGS
below.
.TP
.B u
Put the last recording that was filed back where it came from. One level
only, and a delete cannot be undone this way.
.TP
.B d
Delete the highlighted recording and its sidecars for good. It asks first:
this is the one key here that cannot be taken back.
.TP
.B m
Lock the highlighted recording's frequency out, so that no later scan stops
on it again. The frequency is written into your saved settings, the same list
.BR bandsaunter (1)
maintains, and takes effect on the next scan \[em] a scan already running read
its settings when it started.
.TP
.B "? h"
The list of keys, and which audio player was found.
.TP
.B q
Quit. With a filter in force, Escape clears the filter first.
.SH OPTIONS
.TP
.BI DIRECTORY
Where the recordings are. Defaults to the scanner's output directory, or to
.B $BANDSAUNTER_OUTPUT
when that is set.
.TP
.BI \-\-sort " ORDER"
Start in this order: {sorts}. Date/time is newest first, ordered by the whole
moment \[em] year, month, day, then hour, minute and second; duration is longest
first.
.B time
is accepted as the old name for
.BR date/time .
.TP
.BI \-\-filter " TEXT"
Start with only the recordings matching this, exactly as if it had been typed
at the
.B /
prompt.
.TP
.BI \-\-player " CMD"
The command used to play a recording. The path is appended as its last
argument. By default the first of these that is installed is used:
{players}.
.TP
.B \-\-callsigns
Print every callsign heard in the directory, with the licence it belongs to
and where and when it was heard, then exit.
.TP
.BI \-\-kml " [FILE]"
Write a map of where the stations heard in this directory are licensed, and
exit. Without a filename it writes
.I callsigns.kml
in the recordings directory \[em] the same file a scan writes, so a map built
this way is continued by the next scan rather than duplicated. See
.B THE MAP
below.
.TP
.B \-\-no\-lookup
Do not contact the licence database. Callsigns are still found and still
described from their prefix; only the name and address are missing.
.TP
.B \-\-list
Print one line per recording and exit, without drawing anything. This is what
to use over a pipe, in a script, or anywhere there is no terminal.
.TP
.B \-V ", " \-\-version
Print the version and exit.
.SH SOUND
Playback is handed to whichever player is installed rather than done in the
program: the recordings are ordinary WAV files, every desktop already has
something that plays them, and a browser that cannot start is worse than one
that cannot play. If none is found, everything else still works and the
message says which packages would fix it.
.PP
Over ssh there is usually no sound server at the far end. The browser and its
transcripts work regardless; only Enter has nothing to do.
.SH DETECTED CALLSIGNS
A capture that produced no readable words has a waterfall drawn beside it
instead \[em] a picture of the signal, which for a data burst or a keyed
carrier is the only view there is. The browser marks it, gives the path in
full, and
.B o
prints it: there is no listening to a data burst.
.PP
Under the transcript, headed
.BR "DETECTED CALLSIGNS:" ,
is every callsign heard in it, with the name and location on the licence.
.PP
Finding them is not a matter of one regular expression over the text as
written. A speech recogniser is poor at callsigns \[em] they are not words,
they are said one character at a time \[em] so it breaks them wherever the
speaker paused and writes the phonetic alphabet down verbatim. It also joins
the words back up, hyphenates them, spells them the way they sounded, and
writes down the hesitation in the middle. "KU 0W", "K7 RA",
"kilo uniform zero whiskey", "Whiskey\-One\-Alpha\-Whiskey",
"WhiskeyOneAlphaWhiskey", "wiskey one alfa whisky" and
"whiskey one alpha, uh, whiskey" are all one callsign each, and all of them
are read back correctly.
.PP
A suffix is not part of the callsign. Nothing is joined across a slash, so
.I W1AW/B
is W1AW and not W1AWB, which belongs to nobody.
.PP
Two shapes are recognised, not one. An amateur callsign is a prefix, a
district digit and a suffix \[em] W1AW, KU0W, 2E0ABC. Everything else the FCC
licenses is called the other way round, the letters first and then the digits:
WQVF960 is a GMRS licence and WXG204 an older Part 90 one. On the GMRS and
business channels those are most of what is said.
.PP
False positives are the thing to avoid: a browser that invents callsigns is
worse than one that finds none. So a run of words is only accepted when none
of its parts is an ordinary English word \[em] "or 3. Can you open 4" fits the
shape once the punctuation is gone, and is not a callsign \[em] while a single
token said in one breath is trusted, because W1BOY is a perfectly good
callsign. The GMRS shape is not given that trust: its letters are a run of
two to four, which is the length of a short word, so "west 120" fits it
exactly and a licence prefix never spells anything.
.PP
The lookup uses the FCC's own licence data, published at callook.info, and
falls back to hamdb.org; neither needs an account or a key. The second is not
a spare copy of the first \[em] callook holds United States amateur licences
only, so a German or Canadian callsign is INVALID there and known to the
other, and a source that is down takes only itself with it. The callsign is
the only thing sent, results are cached under
.I ~/.cache/bandsaunter/
so the same net is looked up once however many nights it is recorded, and a
lookup never delays the display: the entry says "looking up" and fills itself
in.
.PP
A GMRS or business callsign is not looked up at all, and says so rather than
saying "unlisted". Every database reachable without an account is an amateur
register and WQVF960 was never in one, so reporting it as missing would blame
the callsign for the absence of a source.
.PP
.B \-\-no\-lookup
contacts nothing at all. Callsigns are still found, and still described from
their own structure \[em] the prefix is allocated by the ITU and the digit is
the US licensing district, so a callsign says which country and which region
it belongs to without any database.
.PP
.B \-\-callsigns
prints every callsign in the directory, who it belongs to, and each frequency
and time it was heard on, then exits.
.PP
US amateur licence records are public by law, and include the street the
licence was issued to, not merely the town. That is what is shown, and what
is written into the map: holding it and not saying so would be worse than
either showing it or not asking for it.
.B \-\-no\-lookup
asks for none of it.
.SH THE MAP
A licence says where its holder is, so a list of callsigns is also a map. The
scanner writes one as it runs and
.B \-\-kml
builds one from recordings already on disk; both write the same file, so
either can carry on from the other.
.PP
Each station is one placemark, not one per transmission: hearing the same
repeater twenty times in an evening is one station, and twenty pins stacked
on the same rooftop would say less than one. The pin holds the callsign, the
licensee, the town, the grid square, and every frequency and time it was
heard on, so clicking it answers "when did I hear this, and where on the
dial".
.PP
The file is added to rather than replaced. A scan on Tuesday continues the
map Monday made, which over a few weeks turns into a picture of what your
aerial can actually reach.
.PP
Where the licence carries no coordinates the grid square is used instead, and
the placemark says so, because a grid square is kilometres across where a
licensed address is a street. A callsign with no licence on file at all is
still recorded, in a folder named
.IR "no location on file" ,
switched off by default: that a station was heard is worth keeping even when
nothing says where it was.
.PP
KML is the format Google Earth uses.
.BR qgis (1),
.BR marble (1)
and OsmAnd open it too, and it is XML, so a scan interrupted halfway through
leaves a file that still opens.
.SH MANAGING THE RECORDINGS
A night's scan leaves hundreds of files, most of which are worth nothing and
a few of which are the reason you left it running. Deciding which is which is
what this program is for, and the keys that act on a recording are meant to
be pressed once each, going down the list.
{filing_prose}
.PP
Each of these moves the whole capture \[em] the
.IR .wav ,
the JSON sidecar, the raw IQ where it was kept, the transcript and the decoded
data \[em] because a recording in one directory and its transcript in another
is a pair nothing will ever put back together. If the move cannot be finished,
whatever has already moved is put back: half a capture in each of two places
is worse than none moved at all.
.PP
The subdirectories are ordinary directories inside the recordings directory,
so a scan writing there never looks into them and never lists what is in
them. To read what is in one, point the browser at it:
.IP
.EX
saunterbrowse ~/bandsaunter/{first_dir}
.EE
.PP
.B u
puts the last one filed back. One step, not a history: it exists so that a
mistyped key costs nothing, not so that an evening's sorting can be unwound.
.PP
.B d
deletes instead, and asks first, because nothing puts that back.
.PP
.B m
is the other half of the same job. A birdie, a pager transmitter or a data
link that fills the recordings directory night after night is not a recording
problem, it is a scanning problem, and this writes the frequency into the
lock-out list in your settings file. The width comes from the
.B lockout_width
setting, so a lock-out is a channel rather than a single point. Locking out a
frequency does not delete what has already been recorded on it \[em] the two
keys are separate on purpose, and pressing both is the usual thing to do.
.SH PICTURES
Some recordings are not sounds. Slow-scan television, the NOAA weather
satellites and the shortwave weather fax stations all send images as audio,
and
.BR bandsaunter (1)
writes what it decodes as a PNG beside the recording.
.PP
Those are marked in the list by what they are \[em] "SSTV Martin M1 320x256" \[em]
and the panel at the top of the screen gives the path of the file in full,
wrapped rather than cut off, because a terminal cannot draw a PNG and saying
exactly what to open is the most useful thing left. A weather satellite pass
has three files: the whole frame, and each of the satellite's two sensors on
its own.
.PP
.B o
prints the picture's path rather than the recording's, for piping into an
image viewer:
.IP
.EX
saunterbrowse \-\-filter sstv \-\-list
xdg\-open "$(saunterbrowse)"
.EE
.PP
Filing a recording moves its pictures with it, and deleting one deletes them.
.SH CALLSIGNS IN MORSE
Most stations on the air never say a word. A repeater, a beacon or an
unattended transmitter sends its callsign in Morse and stops, and what it
sent takes the place of the transcript at the top of the screen, with the
licence it belongs to underneath exactly as for speech. It is searchable with
.B /
like anything else.
.PP
Only the part of it that was not cut in half is looked at for a callsign. A
capture opens when the squelch does, which is partway through a word as often
as not, and what is left of that word can read as a whole one:
.I K1AA
caught halfway through is
.IR K1A ,
which belongs to somebody else.
.BR bandsaunter (1)
describes how that is decided. The full text is shown either way.
.SH DECODED DATA
Where a capture carried data rather than speech, what was decoded takes the
place of the transcript at the top of the screen: the kind of packet, and then
the message. A pager's text, an APRS position report, or the bits and hex of a
remote control. It is searchable with
.B /
like anything else, so "which page mentioned engine 4" is a question that can
be asked here.
.PP
The text comes from the
.I _data.txt
beside the recording, or from the sidecar where there is none.
.BR bandsaunter (1)
describes how it is decoded and what has to be true before a decode is
believed.
.SH TRANSCRIPTS
A transcript appears only where a recogniser produced one, which means the
capture was judged to be speech and
.B bandsaunter\-transcribe
was installed at the time. Where there is none, the panel says which of the
several reasons applies \[em] Morse, data, a bare carrier, or speech that was
never offered to a recogniser \[em] because those want different things done
about them.
.PP
Two places can hold the text: the JSON sidecar records what was recognised
during the scan, and the
.I _transcription.txt
beside the recording is what a later re\-run wrote. The file wins, being the
more recent of the two.
.SH FILES
.TP
.I ~/bandsaunter/
Where recordings are written, unless the saved settings say otherwise.
.TP
.IR frequency \-\- date _ time \- modulation .wav
A recording.
.TP
.IR ... .json
Its measurements and identification.
.TP
.IR ... _transcription.txt
What was said, where a recogniser heard speech.
.TP
.IR ... _data.txt
What was decoded, where the capture carried data.
.TP
.IR {filing_files}
Where the filing keys move recordings to. Created on first use; a scan never
looks in them.
.TP
.I ~/.config/bandsaunter/config.yaml
The settings the
.B m
key writes a locked-out frequency into.
.SH ENVIRONMENT
.TP
.B BANDSAUNTER_OUTPUT
The directory to open, overriding the saved settings.
.SH EXAMPLES
.PP
.RS
.EX
saunterbrowse
.EE
.RE
.PP
Open the scanner's output directory.
.PP
.RS
.EX
saunterbrowse /mnt/recordings \-\-sort frequency
.EE
.RE
.PP
Browse somewhere else, grouped by channel rather than by time.
.PP
.RS
.EX
saunterbrowse \-\-list | grep \-i "mile marker"
.EE
.RE
.PP
Search the transcripts from a script.
.PP
.RS
.EX
saunterbrowse \-\-callsigns
.EE
.RE
.PP
Everyone who identified themselves, and where they were heard.
.PP
.RS
.EX
saunterbrowse \-\-kml ~/heard.kml
.EE
.RE
.PP
The same thing as a map, to open in Google Earth.
.SH EXIT STATUS
0 on a clean exit, 1 when the directory holds no recordings, 2 when it does
not exist or there is no terminal to draw on.
.SH SEE ALSO
.BR bandsaunter (1)
.SH BUGS
The list is read when the browser opens.  Press
.B r
to pick up recordings a running scan has written since.
'''


def main() -> int:
    dirs = [name for _, name, _ in FILING]
    text = PAGE.format(
        date=date.today().isoformat(),
        version=bandsaunter.__version__,
        sorts=", ".join(SORTS),
        players=", ".join(name for name, _ in PLAYERS),
        filing_keys=" ".join(key for key, _, _ in FILING),
        filing_dirs=_english(f"{name}/" for name in dirs),
        filing_list=_english(f"{name}/" for name in dirs),
        filing_files=", ".join(f"{name} /" for name in dirs),
        first_dir=dirs[0],
        filing_prose="\n".join(
            f".TP\n.B {key}\nInto\n.IR {name} /\n\\[em] {why}."
            for key, name, why in FILING))
    text = text.replace("\n\n", "\n")          # troff dislikes blank lines
    target = Path(sys.argv[1] if len(sys.argv) > 1
                  else Path(__file__).parent / "saunterbrowse.1")
    target.write_text(text)
    print(target)
    return 0


if __name__ == "__main__":
    raise SystemExit(main())