From d30397cefa5087675745622b502dd12ab37cfccf Mon Sep 17 00:00:00 2001
From: rmgr <jake@rmgr.dev>
Date: Thu, 30 Nov 2023 08:03:43 +1030
Subject: [PATCH] Add count of times word appears on a site to index.

---
 src/__pycache__/search.cpython-310.pyc | Bin 0 -> 685 bytes
 src/index.py                           |  14 +++++++++++---
 src/search.py                          |   1 +
 3 files changed, 12 insertions(+), 3 deletions(-)
 create mode 100644 src/__pycache__/search.cpython-310.pyc

diff --git a/src/__pycache__/search.cpython-310.pyc b/src/__pycache__/search.cpython-310.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..c7402826f1c52ce28e47c499f6b8c84b197fb854
GIT binary patch
literal 685
zcmYjPy>8S%5T5<B&2dSD03oO;FcN2_j1)ykAPR~Uq=+~PS>|@RT(W2TcGn4s)>5RS
z&nw)O6ui*3R6GC;6=UBO+0lIa?TlwUvpdz!&H!-T{hF#%3h=u-++Pe2Z&B?>1PPL8
zn3FLf9jD0YnD(4$HfCt!n$N{p5Ku%#OEQjCyh@~46B)_)2cYGFWG9d&e=r}UB!~~X
zuop<;PioO9>yA6#l#8Zv>SiyqsxXtY>=1qC`e;JBu<eR)Pf*{X+FJyN^+~#<cl#}I
zWJNt$la@N>@xLv2Sn)NqYzi&+>^*#W)Cw<F0&Tc^dI{#0=c~w5FP_61dt5wovFA%<
zo}U86o;k{r5jcT;um@M@>Etu2L|e*^Z}w#2ifmR&^?h`1t1=LiCV^MADg*BgTvvrO
z9P16j)_UfG(AAYPAu4M8N(NDzS?SU!h`#AC=(FX0u;_Vs*n9F#cx04qv<qbM6U<}G
z`|ovjR?Ss*UR<b5s>|&qzES0LR;tXJ$<{KeuS2xC;cg7<3xpvZkOYPIn2=pUZxc$%
z%fIF+y3;`r-?}F=I4)qi`7kj;7&b=h+1F8B7^^nzC3#*JbCu_TVQWE{s&T5%(wBJ;
co^%<K!+9ket&X}!wz~*JI>ahaX+n3&f0}=%=l}o!

literal 0
HcmV?d00001

diff --git a/src/index.py b/src/index.py
index 781b9b6..83d4342 100755
--- a/src/index.py
+++ b/src/index.py
@@ -23,9 +23,17 @@ def build_index():
                     if not word in ignored_words:
                         if not word in dictionary:
                             dictionary[word] = []
-                        if not url.strip() in dictionary[word]:
-                            dictionary[word].append(url.strip())
-
+                        matching_urls = list(filter(lambda entry: entry["url"] == url.strip(), dictionary[word]))
+                        if len(matching_urls) == 0:
+#                        if not url.strip() in dictionary[word]:
+                            entries = dictionary[word]
+                            entry = {"url": url.strip(), "count": 1}
+                            dictionary[word].append(entry)
+                        else:
+                            entries = dictionary[word]
+                            entry = matching_urls[0]
+                            entry["count"] += 1
+                            entries.sort(reverse=True, key=lambda entry: entry["count"])
         index.write(json.dumps(dictionary))
 
 if __name__ == "__main__":
diff --git a/src/search.py b/src/search.py
index 1a71241..e5389f8 100755
--- a/src/search.py
+++ b/src/search.py
@@ -18,6 +18,7 @@ def search(query):
             q = q.lower()
             if q in index:
                 result.append(index[q])
+#        result.sort(reverse= True,key=lambda entry: int(entry.count))
         print(result)
         return result