Return to Question

diff --git a/DeploymentSites/Main/file1.txt b/DeploymentSites/Main/file1.txt index a3fb2ed..4d6f587 100644 --- a/DeploymentSites/Main/file1.txt +++ b/DeploymentSites/Main/file1.txt @@ -3,2 +3,3 @@ context context +added line context @@ -7,2 +8,3 @@ context context +added line context @@ -11,2 +13,3 @@ context context +added line context @@ -15,2 +18,3 @@ context context +different added line context @@ -19,2 +23,3 @@ context context +different added line context @@ -23,2 +28,3 @@ context context +different added line context @@ -27,2 +33,3 @@ context context +even more different added line context @@ -31,2 +38,3 @@ context context +even more different added line context 

diff --git a/file1.txt b/file1.txt index a3fb2ed..4d6f587 100644 --- a/file1.txt +++ b/file1.txt @@ -3,2 +3,3 @@ context context +added line context @@ -7,2 +8,3 @@ context context +added line context @@ -11,2 +13,3 @@ context context +added line context @@ -15,2 +18,3 @@ context context +different added line context @@ -19,2 +23,3 @@ context context +different added line context @@ -23,2 +28,3 @@ context context +different added line context @@ -27,2 +33,3 @@ context context +even more different added line context @@ -31,2 +38,3 @@ context context +even more different added line context 

BEGIN { hunk = "" buildhunk = 0 } function writeHunk() { if (length(hunk) > 0) { print hunk > "hunk.tmp" close("hunk.tmp") cmd = "cat hunk.tmp | md5" cmd | getline md5 close(cmd) if (!(md5 in md5s)) { print hunk > "hunk-" md5 ".txt" md5s[md5] = 1 } } } /^@@|^diff/ { writeHunk() hunk = "" buildhunk = ($1 == "@@") ? 1 : 0 } /^[ +-]/ { if (buildhunk) { hunk = hunk $0 "\n" } } END { writeHunk() system("rm hunk.tmp") for (md5 in md5s) { print "hunk-" md5 ".txt" } } 

BEGIN { hunk = "" buildhunk = 0 } function writeHunk() { if (length(hunk) > 0) { print hunk > "hunk.tmp" close("hunk.tmp") cmd = "cat hunk.tmp | md5" cmd | getline md5 close(cmd) if (!(md5 in hunkfiles)) { hunkfilename = "hunk-" md5 ".txt" print hunk > hunkfilename  hunkfiles[md5] = hunkfilename } } } /^@@|^diff/ { writeHunk() hunk = "" buildhunk = ($1 == "@@") ? 1 : 0 } /^[ +-]/ { if (buildhunk) { hunk = hunk $0 "\n" } } END { writeHunk() system("rm hunk.tmp") for (md5 in hunkfiles) { print hunkfiles[md5] } } 

Example

Suppose the commit's patch looks like this (reduced to 1 line of context below for clarity's sake):

diff --git a/DeploymentSites/Main/file1.txt b/DeploymentSites/Main/file1.txt index a3fb2ed..4d6f587 100644 --- a/DeploymentSites/Main/file1.txt +++ b/DeploymentSites/Main/file1.txt @@ -3,2 +3,3 @@ context context +added line context @@ -7,2 +8,3 @@ context context +added line context @@ -11,2 +13,3 @@ context context +added line context @@ -15,2 +18,3 @@ context context +different added line context @@ -19,2 +23,3 @@ context context +different added line context @@ -23,2 +28,3 @@ context context +different added line context @@ -27,2 +33,3 @@ context context +even more different added line context @@ -31,2 +38,3 @@ context context +even more different added line context 

I want to be able to identity that there are only 3 unique hunks, and see what they are. Namely:

Unique hunk 1:

 context +added line context 

Unique hunk 2:

 context +different added line context 

Unique hunk 3:

 context +even more different added line context