sm-transcript 0.0.3

data/lib/sm_transcript/word.rb

@@ -0,0 +1,31 @@
+# $Id: word.rb 182 2010-03-12 22:07:34Z pwilkins $
+# Copyright (c) 2010 Massachusetts Institute of Technology
+# see LICENSE.txt for license text
+
+module SmTranscript
+  class Word
+    attr_reader :start_time
+    attr_reader :end_time
+    attr_reader :word
+    
+    def initialize( start_time, end_time, word )
+      @start_time = start_time
+      @end_time = end_time
+      @word = apply_word_rules(word)
+    end
+    
+    def apply_word_rules(word)
+      case word
+      when "i" # (English) "i" appearing as a word is capitalized
+        word.upcase
+      when "i'm", "i've" # (English) "i" as personal pronoun is capitalized
+        word.capitalize
+      when "iranian"  # (English) proper nouns are capitalized
+        word.capitalize
+      else
+        word
+      end
+    end
+    
+  end
+end

data/lib/sm_transcript/wrd_reader.rb

@@ -0,0 +1,42 @@
+# $Id: wrd_reader.rb 182 2010-03-12 22:07:34Z pwilkins $
+# Copyright (c) 2010 Massachusetts Institute of Technology
+# see LICENSE.txt for license text
+
+require 'rubygems'
+require 'extensions/kernel'
+require_relative 'word'
+
+module SmTranscript
+  class WrdReader
+    attr_reader :metadata
+    attr_reader :words
+
+    def self.from_file(file_name)
+      # p File.expand_path(file_name)
+      new(File.open(file_name))
+    end
+
+    def initialize(src_file)
+      @metadata = {}
+      @words = []
+      parse_metadata()
+      parse_words(src_file)
+    end
+
+    def parse_metadata()
+      # there is currently no metadata in .wrd files
+    end
+
+    def parse_words(src_file)
+      src_file.each do |ln|
+        # line is expected to contain two integers separated by a space, 
+        # followed by a space and one or more words.  The words may contain
+        # characters or an apostrophe
+        ln.scan(/^\d* \d* [\w']* *[\w']*$/) do |t|
+          arr = t.split
+          @words << SmTranscript::Word.new(arr[0], arr[1], arr[2])
+        end
+      end
+    end
+  end
+end

data/test/Rakefile

@@ -0,0 +1,14 @@
+# $Id: Rakefile 182 2010-03-12 22:07:34Z pwilkins $
+
+require 'rubygems'
+require 'rake'
+require 'rake/testtask'
+
+task :default => [:test_units]
+
+desc "Run basic tests"
+Rake::TestTask.new("test_units") { |t|
+  t.pattern = 'test_*.rb'
+  t.verbose = false
+  t.warning = false
+}

data/test/results/IIHS_Diane_Davis_Nov2009.seg

@@ -0,0 +1,425 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<document fileName="/Users/mckinney/Developer/Projects/SpokenMedia/workspace/standalone/results/IIHS_Diane_Davis_Nov2009.seg">
+<lecture title="NA" keywords="global">
+<segment id="1" title="global">
+11406 11500 oh
+11500 11585 i
+11585 11790 think
+11790 12188 there're
+12188 12584 several
+12584 12951 critical
+12951 13438 questions
+13438 13560 of
+13560 13850 ones
+13850 13995 that
+13995 14405 i
+14405 14822 found
+14822 14943 in
+14943 15300 steady
+15300 15745 most
+15745 16559 myself
+17214 17415 are
+17415 17813 questions
+17813 17937 of
+17937 18630 insecurity
+18630 18775 into
+18775 19510 violence
+19510 20055 i
+20055 20445 see
+20445 20853 those
+20853 21200 and
+21200 22070 some
+22070 22655 pervasive
+22655 22770 the
+22770 23260 class
+23260 23553 much
+23553 23680 of
+23680 23756 a
+23756 24108 global
+24108 24516 found
+25147 25277 and
+25277 25427 i
+25427 25947 think
+27342 27461 have
+27461 27522 a
+27522 27677 lot
+27677 27781 to
+27781 28032 do
+28032 28357 with
+28357 28422 her
+28422 28722 and
+28722 28967 devil
+28967 29672 transition
+29672 29963 that
+29963 30217 in
+30217 30286 the
+30286 30762 developing
+30762 30936 world
+30936 31172 is
+31172 31777 facebook
+31777 31953 pull
+31953 32034 the
+32034 32287 climb
+32287 32827 economic
+32827 34027 globalization
+34027 34312 never
+34312 34862 flat
+35122 35285 it's
+35285 35350 a
+35350 35685 fairly
+35685 36235 standard
+36235 36460 way
+36460 36548 of
+36548 37129 understanding
+37129 37665 the
+37665 37943 crime
+37943 38040 and
+38040 38570 violence
+38570 38972 so
+40637 40696 i
+40696 40905 think
+40905 41057 it's
+41057 41432 import
+41432 41472 and
+41472 41705 because
+41705 41787 it
+41787 42172 means
+42172 42302 is
+42302 42687 that
+42687 43083 problem
+43083 43191 of
+43191 43306 r
+43306 43907 times
+44811 44972 and
+44972 45157 then
+45157 45619 many
+45619 46167 developing
+46167 46903 countries
+46903 47042 in
+47042 47402 different
+47402 47782 regions
+47782 47892 of
+47892 47982 the
+47982 48317 world
+48317 48421 are
+48421 49423 facing
+49423 50356 insecurity
+50356 50582 and
+50582 51492 violence
+51766 52265 that
+53319 53525 and
+53525 53662 a
+53662 53821 lot
+53821 53961 to
+53961 54096 do
+54096 54267 with
+54267 54436 the
+54436 54916 changing
+54916 55391 nature
+55391 55656 of
+55656 55938 an
+55938 56182 urban
+56182 56898 economies
+56898 57071 and
+57071 57214 how
+57214 57635 they
+57874 58346 linked
+58346 58459 to
+58459 58566 the
+58566 59276 global
+59276 59936 economy
+59936 60151 so
+60151 60263 and
+60263 60685 that's
+61248 61343 i
+61343 61898 think
+61898 63003 come
+63003 63518 pervasive
+63518 64288 challenge
+67678 67836 is
+67836 68090 that
+68090 68239 is
+68239 68457 one
+68457 68557 and
+68557 69049 two
+69049 69146 are
+69146 69451 three
+69451 70386 specializations
+70386 70526 that
+70526 70776 when
+70776 71121 means
+71121 71427 in
+71769 71906 and
+71906 72691 interconnected
+72691 73066 the
+73066 73371 global
+73371 73866 world
+73866 74411 aware
+74765 75695 technology
+75695 75895 and
+75895 76625 treat
+76625 77568 endowment
+78727 78947 of
+78947 79777 communication
+79777 80012 and
+80012 80287 this
+81408 81577 i
+81577 81792 d
+81792 82247 l
+82247 83052 ideology
+83052 83167 of
+83167 83368 those
+83368 83437 are
+83437 83572 all
+83572 84132 important
+84132 84202 to
+84875 85342 aspects
+85342 85470 of
+85470 85791 that
+85791 85915 i'm
+85915 86000 the
+86000 86660 planning
+86660 86930 to
+86930 87295 kept
+88377 88488 but
+88488 88636 i
+88636 88894 would
+88894 89157 say
+89157 89903 definitely
+89903 90337 need
+90337 90426 to
+90426 91267 people
+91267 91641 who
+91641 92057 are
+92739 92857 i
+92857 93002 had
+93002 93312 the
+93312 93544 think
+93544 93942 about
+93942 94487 them
+94487 94777 meaning
+94777 95260 regulator
+95260 95597 people
+95597 95652 and
+95652 95791 now
+95791 95947 but
+95947 96862 organizations
+96862 97052 howell
+97052 97782 organizations
+97782 98102 function
+98102 98397 because
+98397 99367 organizations
+100540 100751 there
+100751 100916 it's
+100916 100971 a
+100971 101366 whole
+101366 101991 literature
+101991 102072 in
+102072 102102 a
+102102 102567 field
+102567 102726 of
+102726 103460 organizational
+103460 103916 fury
+103916 104143 there
+104143 104306 would
+104306 104456 be
+104456 104869 important
+104869 105451 understand
+105451 105775 amiga
+105775 106191 small
+106191 106256 is
+106256 106518 that
+106518 106675 is
+106675 106896 our
+106896 107196 local
+107196 107776 government
+107776 107906 our
+107906 108172 rap
+108172 109141 community
+109141 109511 iranian
+109511 109691 g
+109691 109964 l
+110415 110638 and
+110638 111084 something
+111084 111284 as
+111284 111677 large
+111677 111939 as
+112581 112952 steak
+112952 113167 ever
+113167 113497 meant
+113497 113662 and
+113662 114072 national
+114072 114836 government
+114836 115485 maybe
+115485 116278 at
+116278 116382 the
+116382 116602 u
+116602 116847 n
+116847 116952 r
+116952 117042 a
+117042 117492 global
+117492 118022 agency
+118022 118377 news
+118377 119171 activities
+119584 120310 influence
+121832 121927 and
+121927 122050 the
+122050 122358 small
+122358 122659 scale
+122659 122781 so
+122781 122876 i
+122876 123140 think
+123140 124361 organization
+124361 125033 analysis
+125033 125141 is
+125141 125221 a
+125221 125461 very
+125461 126021 important
+126021 126274 okay
+129718 130024 line
+130024 130126 is
+130126 130540 lambda
+130540 130728 t
+130728 131096 v
+131096 131291 for
+131291 131866 television
+131866 132116 the
+132116 132381 only
+132381 132631 about
+132631 132964 it
+132964 133061 i
+133061 133423 think
+133423 133791 and
+133791 134086 there's
+134086 134285 a
+134285 134496 lot
+134496 134596 of
+134596 134764 x
+134764 135074 segment
+135074 135361 about
+135361 135671 that
+135748 135839 and
+135839 135967 i
+135967 136207 didn't
+136207 136422 think
+136422 136547 that
+136547 136787 that
+136787 137235 eminently
+137235 137311 to
+137311 137413 the
+137413 137907 challenges
+137907 138027 the
+138027 138277 town
+138277 138432 and
+138432 138543 it's
+138543 139365 hard
+139365 139918 are
+139918 140118 how
+140118 140182 to
+140182 140442 get
+140442 140717 there
+141033 141442 yeah
+141442 141657 so
+141657 141795 in
+141795 142041 what
+142041 142173 are
+142173 142338 the
+142338 143080 strategic
+143080 143260 aims
+143260 143662 least
+143662 143920 okay
+143920 144155 many
+144155 144265 here
+144265 144395 and
+144395 144605 this
+144605 144840 meeting
+144840 145385 whatever
+145385 145556 to
+145556 145740 dick
+145740 146073 steps
+146073 146390 any
+146390 146485 to
+146485 146645 be
+146645 147000 take
+147000 147620 ten
+147879 148133 where
+148133 148284 you
+148284 148642 can
+148642 149163 accomplish
+149163 149507 something
+149507 149588 in
+149588 149689 the
+149689 149988 short
+149988 150238 term
+150238 150520 right
+150520 150943 away
+151340 151574 but
+151574 152461 also
+152461 152600 you
+152600 152825 know
+152825 152892 the
+152892 153045 the
+153045 153127 you're
+153127 153295 not
+153295 153422 going
+153422 153550 to
+153550 154016 accomplish
+154016 154395 everything
+154395 154543 that
+154543 154725 you're
+154725 155005 leading
+155005 155193 out
+155193 155360 in
+155360 155564 year
+155564 155815 vision
+155815 156135 and
+156323 156847 so
+157318 157455 you
+157455 157735 want
+157735 157856 to
+157856 158175 make
+158175 159070 progress
+159725 160753 continually
+160753 161005 every
+161005 161499 states
+161499 161776 has
+161776 161800 a
+161800 162055 has
+162055 162315 some
+162315 162402 of
+162402 162475 the
+162475 162817 small
+162817 163585 success
+163795 164185 but
+164185 164390 for
+164390 164432 a
+164432 164650 need
+164650 164725 for
+164725 164865 its
+164865 165250 allies
+165250 165680 success
+165680 166000 because
+166000 166135 you
+166135 166935 can't
+166935 167295 put
+167295 167413 an
+167413 168470 institution
+168906 169036 it's
+169036 169135 and
+169135 169483 develop
+169483 169540 an
+169540 170090 institution
+170090 170270 like
+170270 170539 to
+170539 171150 emulate
+171769 171942 your
+171942 172137 have
+172137 172265 in
+172265 173159 mind
+173159 173270 of
+173270 173339 the
+173339 173770 night
+</segment>
+</lecture>
+</document>
+