fedran-languages/miwafu
2
0
Fork 0
Code Issues Pull requests Projects Releases Packages Activity

Modifying the dictionary builder to output individual directories.

Browse source
This commit is contained in:
Dylan R. E. Moonfire 2017-05-09 19:05:40 -05:00
parent 129f05ecb0
commit 86ef5ac654
1 changed files with 39 additions and 12 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

49
bin/create-dictionary-markdown
View file

@ -14,6 +14,17 @@ binmode(STDERR, ":utf8");
# Modules # Modules
use File::Basename; use File::Basename;
use Getopt::Long;
# Variables
my $EXT = ".markdown";
my $REPO_DIR = dirname($0) . "/..";
my $BUILD_DIR = "$REPO_DIR/build";
&GetOptions(
"output|o=s" => \$BUILD_DIR,
"ext|e=s" => \$EXT,
);
# #
# Paths # Paths
@ -21,9 +32,7 @@ use File::Basename;
# These scripts are designed to work within the Git repository and # These scripts are designed to work within the Git repository and
# makes assumptions of all the relative paths and outputs. # makes assumptions of all the relative paths and outputs.
my $REPO_DIR = dirname(dirname($0)); my $DICT_MARKDOWN = "$BUILD_DIR/index.markdown";
my $BUILD_DIR = "$REPO_DIR/build";
my $DICT_MARKDOWN = "$BUILD_DIR/dictionary.markdown";
my $DICT_DIR = "$REPO_DIR/src/dictionary"; my $DICT_DIR = "$REPO_DIR/src/dictionary";
# Make sure the build directory exists. # Make sure the build directory exists.
@ -38,14 +47,17 @@ unless (-d $BUILD_DIR)
# #
# Create the initial Markdown file. # Create the initial Markdown file.
open DICT, ">:encoding(UTF-8)", $DICT_MARKDOWN my ($DICT, $SYB);
print STDERR "Writing to $DICT_MARKDOWN\n";
open $DICT, ">:encoding(UTF-8)", $DICT_MARKDOWN
or die "Cannot write dictionary file ($!)"; or die "Cannot write dictionary file ($!)";
# Write out the front matter. # Write out the front matter.
print DICT join( print $DICT join(
"\n", "\n",
"---", "---",
"title: Miwāfu Dictionary", "title: Miwāfu Dictionary",
"breadcrumbTitle: Dictionary",
"---"), "\n\n"; "---"), "\n\n";
# Loop through the directories in the dictionary. # Loop through the directories in the dictionary.
@ -54,6 +66,10 @@ for my $s (sort(glob("$DICT_DIR/*")))
# Figure out the basename. # Figure out the basename.
my $bs = basename($s); my $bs = basename($s);
# Open up the syllable file.
open $SYB, ">:encoding(UTF-8)", "$BUILD_DIR/$bs.markdown"
or die "Cannot write $bs dictionary file ($!)";
# Determine if we have any entries in here. # Determine if we have any entries in here.
my @w = sort(glob("$s/*.markdown")); my @w = sort(glob("$s/*.markdown"));
next unless @w; next unless @w;
@ -61,17 +77,22 @@ for my $s (sort(glob("$DICT_DIR/*")))
# Write out the entry. # Write out the entry.
print STDERR "Processing: $bs ($w entries)\n"; print STDERR "Processing: $bs ($w entries)\n";
print DICT "# $bs\n\n"; print $DICT "# $bs\n\n";
print $SYB "---\ntitle: Miwāfu Dictionary - $bs\n---\n\n# $bs\n\n";
# Go through each of these entries. # Go through each of these entries.
for $w (@w) for $w (@w)
{ {
process_word($w); process_word($w, $bs);
} }
# Close the file.
close $SYB;
} }
# Finish up the dictionary. # Finish up the dictionary.
close DICT; close $DICT;
# #
# Finished # Finished
@ -86,7 +107,7 @@ print STDERR "Done\n";
sub process_word sub process_word
{ {
# Pull out the entries from the file. # Pull out the entries from the file.
my ($file) = @_; my ($file, $bs) = @_;
# Read in this file and process the entries. # Read in this file and process the entries.
open WORD, "<:encoding(UTF-8)", $file; open WORD, "<:encoding(UTF-8)", $file;
@ -148,7 +169,12 @@ sub process_word
foreach $word (sort(keys(%defs))) foreach $word (sort(keys(%defs)))
{ {
# Start by formatting the word. # Start by formatting the word.
my $buffer = "**$word**:"; my $slug = $word;
$slug =~ tr/[aeiouáéíóúàèìòùāēīōū]/[aeiouaeiouaeiou]/;
print $DICT "[$word]($bs/$slug$EXT):";
print $SYB "[$word]($slug$EXT):";
my $buffer = "";
# Add in the parts of speech. # Add in the parts of speech.
for $pos (qw(noun verb adj adv pro mark)) for $pos (qw(noun verb adj adv pro mark))
@ -163,6 +189,7 @@ sub process_word
$buffer .= join(" ", @{$defs{$word}{$pos}}); $buffer .= join(" ", @{$defs{$word}{$pos}});
} }
print DICT "$buffer\n\n"; print $DICT "$buffer\n\n";
print $SYB "$buffer\n\n";
} }
} }