From f14622e94083c72d8b3bd60c780416de68a5b50c Mon Sep 17 00:00:00 2001
From: Cristina Cochior <clcochior@gmail.com>
Date: Wed, 17 Apr 2019 18:36:12 +0200
Subject: [PATCH] added the new python file

---
 static/files/.DS_Store                  | Bin 21508 -> 24580 bytes
 static/files/00. Pushing Scores/00.json |  13 ------------
 textedit.py                             |  26 ++++++++++++++++++++++++
 3 files changed, 26 insertions(+), 13 deletions(-)
 delete mode 100644 static/files/00. Pushing Scores/00.json
 create mode 100644 textedit.py

diff --git a/static/files/.DS_Store b/static/files/.DS_Store
index b1d674c6e60e3ddc7fe1b9e2a0265a14bda50323..b10cdea462ce763ca8385adb0ad6bdc009edccdd 100644
GIT binary patch
delta 223
zcmZo!!Ps(uae@>V3l{@}0uKX&0nbDgZAQ(F0o$1;8@RAc=C;V$oGOsaH2ITN_+)8e
z!O5S5G$$LG<xid{tj*29z{mgw9NZfV#aTA1^E_c@<N->BZEh6q;@Q|B&&(*aSyu55
z&t_qZ`%Du{To^eg3s|IVHaE^<1}pQlu49@!ML2kK63~v#rCKe_P?Zj{Y!IUzfVMEW
wGB5}L9fxq_#=_UkllfgdC&#!f-Rx+&kr8SLGvj7KkI&qj6+E7BPi)Wx06h^sApigX

delta 463
zcmZoUz}T{aae@?=1vdkO0uKX&0rx}|ZAQI~0o$1uD{!!IGBSVx2lwWMlHx3z)p?#U
zGxAO55eVDNXr9ajWJEB!OimR@-kc=R#S<U~R4l|`0EBuB3Jd`Zr3}Rk84Q^Wc?{`5
zelSBaLq0<hLn=dYN^x>dQht68$ap*&CO;4ouV>H}#IFirY;L}bOG;@;G6TbnJc|~v
z%kh|wtS<$pJ|RqhOxBYWXJT-e%&6hHIYeO!&&CoVCPt3Qg*vI5OIcExCYR_WZZ0s$
zV%|JKHJK3@s0>U{%mP;9rCZCy$O;Zb1Cu(YNyfLp3Kf8g*nk)a9DuRG;L5-t0Mv|#
mnazS6ubC(FyLe9a=i!(f<FarvqyDMMEXLQs+7}CY@Bjev=3wCf

diff --git a/static/files/00. Pushing Scores/00.json b/static/files/00. Pushing Scores/00.json
deleted file mode 100644
index 9bc2eff..0000000
--- a/static/files/00. Pushing Scores/00.json	
+++ /dev/null
@@ -1,13 +0,0 @@
-{
-  "id": "00.",
-  "name": "Yes",
-  "email": "sure@whynot.com",
-  "friend": "Y",
-  "content": "A sound file.",
-  "files":[
-  	"files/00. Pushing Scores/Participants.txt",
-    "files/00. Pushing Scores/PushingScores.html",
-    "files/00. Pushing Scores/events.txt"
-
-  ]
-}
diff --git a/textedit.py b/textedit.py
new file mode 100644
index 0000000..dbd29b1
--- /dev/null
+++ b/textedit.py
@@ -0,0 +1,26 @@
+# this code is split in two parts:
+# going through the description html files and gathering the interesting words in a json file;
+# and going through the files again to replace words that also appear in the json with an a href version
+
+import sys, os
+import nltk
+from nltk import word_tokenize
+from nltk.util import trigrams
+
+# text analysis
+def analysis(file):
+    # print("yes")
+    file_trigrams = trigrams(content)
+    print(file_trigrams)
+
+
+
+# reading each individual html file
+path = "static/files/"
+for path, subdirs, files in os.walk(path):
+    for name in files:
+        if name.endswith('html'):
+            file = os.path.join(path, name)
+            with open(file) as f:
+                content = f.read()
+            analysis(content)