7shi 7shi

## README.md

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                7shi
                / README.md
            
            
              Last active
              June 5, 2020 09:09
            
              
                [py][sqlite3] get a page from the Wikipedia's dump
              
          
    These files have been moved.

https://github.com/7shi/wiktionary-tools/blob/master/python/conv_index.py
https://github.com/7shi/wiktionary-tools/blob/master/python/mediawiki.py


## Novial.tsv

          
            me
            FE me

            
              vu
              F vous (sg.)

            
              lo
              F il, lui | -o male

            
              nus
              F nous | -s pl.

            
              vus
              F vous | -s pl.

            
              los
              lo + -s pl.

            
              disi
              E this, D dieser

            
              ti
              E that, R то (to), L iste; -i adj.

            
              hir
              E here, D hier

            
              dar
              D da, dort, E there

## ssml_nov.py
# CC0 http://creativecommons.org/publicdomain/zero/1.0/

import getopt, re, sys

lang = "sk-SK" # ca-ES, cs-CZ, de-CH, de-DE, hr-HR, hu-HU, pl-PL, ro-RO, ru-RU, sk-SK, sl-SI
testwords = [] #"nusen patre intestines familie lause".split()

phonemes = {}

def setphonemes(phs):

## ssml_ile.py
# CC0 http://creativecommons.org/publicdomain/zero/1.0/

import getopt, re, sys

lang = "ro-RO" # ca-ES, pl-PL, ro-RO, sk-SK, sl-SI
testwords = [] #"intercalar forme familie rapidmen duplic café ínpossibil".split()

phonemes = {}

def setphonemes(phs):

## ssml_epo.py
# CC0 http://creativecommons.org/publicdomain/zero/1.0/

phonemes = {}

def setphonemes(phs):
    for ph in phs.split():
        p1, p2 = ph.split(",")
        phonemes[p1] = p2

setphonemes("a,A b,B c,TS ĉ,CH d,D e,E f,F g,G ĝ,JH h,H")

## Makefile
TARGET = alfabeto
MKWAV  = ~/bin/wintts -o $$wav `python ssml_lfn.py -l pl-PL -f $$txt`
SILENT = ffmpeg -t 00:00:02 -f s16le -i /dev/zero -acodec pcm_s16le -ar 22050 -ac 1 $$wav
MKAVI  = ffmpeg -loop 1 -i $$png -i $$wav -vcodec mpeg4 -acodec pcm_s16le -shortest $$avi

all: $(TARGET).mp4

clean:
	rm -f $(TARGET).mp4 $(TARGET).lst *.avi *.png *.wav

## Makefile
TARGET = foo
MKWAV  = ~/bin/wintts -o $$wav `python ssml_lfn.py -l pl-PL -f $$txt`
SILENT = ffmpeg -t 00:00:02 -f s16le -i /dev/zero -acodec pcm_s16le -ar 22050 -ac 1 $$wav
MKAVI  = ffmpeg -loop 1 -i $$png -i $$wav -vcodec mpeg4 -acodec pcm_s16le -shortest $$avi

all: $(TARGET).mp4

clean:
	rm -f $(TARGET).mp4 $(TARGET).lst $(TARGET)-*.avi $(TARGET)-*.wav $(TARGET)-*.png $(TARGET)-*.txt

## ssml_lfn.py
# CC0 http://creativecommons.org/publicdomain/zero/1.0/

import getopt, sys

options = "l:f:"
def usage():
    print("usage: %s -l lang (-f file | text ...)" % sys.argv[0])
    exit(1)

_phons = {}

## calc.py
# pip install python-levenshtein
import itertools, Levenshtein

with open("swadesh.csv") as f:
    data = [line.split(",") for line in f.readlines()]
slang = "English|Esperanto|Ido|Novial|Interlingue|Interlingua"
langs = slang.split("|")
count = len(langs)
split = "|----|%s|" % "|".join(["---:"] * count)

## Convert.fsx
// https://sites.google.com/site/noviallexike/novial-lexike-1930

// https://gist.github.com/7shi/de072cd867f3899aa285bc9343110bff
#load "XmlParser.fsx"

open System.IO
open XmlParser

do
use xp = new XmlParser(new StreamReader("novial.html"))
	me	FE me
	vu	F vous (sg.)
	lo	F il, lui \| -o male
	nus	F nous \| -s pl.
	vus	F vous \| -s pl.
	los	lo + -s pl.
	disi	E this, D dieser
	ti	E that, R то (to), L iste; -i adj.
	hir	E here, D hier
	dar	D da, dort, E there
	# CC0 http://creativecommons.org/publicdomain/zero/1.0/

	import getopt, re, sys

	lang = "sk-SK" # ca-ES, cs-CZ, de-CH, de-DE, hr-HR, hu-HU, pl-PL, ro-RO, ru-RU, sk-SK, sl-SI
	testwords = [] #"nusen patre intestines familie lause".split()

	phonemes = {}

	def setphonemes(phs):
	# CC0 http://creativecommons.org/publicdomain/zero/1.0/

	import getopt, re, sys

	lang = "ro-RO" # ca-ES, pl-PL, ro-RO, sk-SK, sl-SI
	testwords = [] #"intercalar forme familie rapidmen duplic café ínpossibil".split()

	phonemes = {}

	def setphonemes(phs):
	TARGET = alfabeto
	MKWAV = ~/bin/wintts -o $$wav `python ssml_lfn.py -l pl-PL -f $$txt`
	SILENT = ffmpeg -t 00:00:02 -f s16le -i /dev/zero -acodec pcm_s16le -ar 22050 -ac 1 $$wav
	MKAVI = ffmpeg -loop 1 -i $$png -i $$wav -vcodec mpeg4 -acodec pcm_s16le -shortest $$avi

	all: $(TARGET).mp4

	clean:
	rm -f $(TARGET).mp4 $(TARGET).lst .avi .png *.wav
	TARGET = foo
	MKWAV = ~/bin/wintts -o $$wav `python ssml_lfn.py -l pl-PL -f $$txt`
	SILENT = ffmpeg -t 00:00:02 -f s16le -i /dev/zero -acodec pcm_s16le -ar 22050 -ac 1 $$wav
	MKAVI = ffmpeg -loop 1 -i $$png -i $$wav -vcodec mpeg4 -acodec pcm_s16le -shortest $$avi

	all: $(TARGET).mp4

	clean:
	rm -f $(TARGET).mp4 $(TARGET).lst $(TARGET)-.avi $(TARGET)-.wav $(TARGET)-.png $(TARGET)-.txt
	# CC0 http://creativecommons.org/publicdomain/zero/1.0/

	import getopt, sys

	options = "l:f:"
	def usage():
	print("usage: %s -l lang (-f file \| text ...)" % sys.argv[0])
	exit(1)

	_phons = {}
	# pip install python-levenshtein
	import itertools, Levenshtein

	with open("swadesh.csv") as f:
	data = [line.split(",") for line in f.readlines()]
	slang = "English\|Esperanto\|Ido\|Novial\|Interlingue\|Interlingua"
	langs = slang.split("\|")
	count = len(langs)
	split = "\|----\|%s\|" % "\|".join(["---:"] * count)
	// https://sites.google.com/site/noviallexike/novial-lexike-1930

	// https://gist.github.com/7shi/de072cd867f3899aa285bc9343110bff
	#load "XmlParser.fsx"

	open System.IO
	open XmlParser

	do
	use xp = new XmlParser(new StreamReader("novial.html"))