From 311aa5d8d960dcfb64a762a5f597244001b94023 Mon Sep 17 00:00:00 2001
From: aszlig <aszlig@redmoonstudios.org>
Date: Tue, 14 Apr 2015 06:55:48 +0200
Subject: [PATCH] python-wrapper: Handle strings at the beginning.

This should fix #7366 for now, but using the (IMHO) pragmatic approach
of extending the sed expression to recognize strings.

However, this approach is obviously not parsing the full AST, nor does
it wrap Python itself (as pointed out by @spwhitt in #7366) but tries to
match Python strings as best as possible without getting TOO unreadable.

We also use a little bit of Nix to help generating the SED expression,
because doing the whole quote matching block over and over again would
be quite repetitious and error-prone to change. The reason why I'm using
imap here is that we need to have unique labels to avoid jumping into
the wrong branch.

So the new expression is not only able to match continous regions of
triple-quoted strings, but also regions with only one quote character
(even with escaped inner quotes) and empty strings.

However, what it doesn't correctly recognize is something like this:

"string1" "string2" "multi
line
string"

Which is very unlikely that we'll find something like this in the wild.
Of course, we could handle it as well, but it would mean that we need to
substitute the current line into hold space until we're finished parsing
the strings, branch off to another label where we match multiline
strings of all sorts and swap hold/pattern space and finally print the
result. So to summarize: The SED expression would be 3 to 4 times bigger
than now and we gain very little from that.

Signed-off-by: aszlig <aszlig@redmoonstudios.org>
---
 .../python-modules/generic/wrap.sh            |  7 +----
 pkgs/top-level/python-packages.nix            | 26 +++++++++++++++++++
 2 files changed, 27 insertions(+), 6 deletions(-)

diff --git a/pkgs/development/python-modules/generic/wrap.sh b/pkgs/development/python-modules/generic/wrap.sh
index e343536b8fa8..220ddf26b30f 100644
--- a/pkgs/development/python-modules/generic/wrap.sh
+++ b/pkgs/development/python-modules/generic/wrap.sh
@@ -26,12 +26,7 @@ wrapPythonProgramsIn() {
             # dont wrap EGG-INFO scripts since they are called from python
             if echo "$i" | grep -v EGG-INFO/scripts; then
                 echo "wrapping \`$i'..."
-                sed -i "$i" -re '1 {
-                    /^#!/!b; :r
-                    /\\$/{N;b r}
-                    /__future__|^ *(#.*)?$/{n;b r}
-                    /^ *[^# ]/i import sys; sys.argv[0] = '"'$(basename "$i")'"'
-                }'
+                sed -i "$i" -re '@magicalSedExpression@'
                 wrapProgram "$i" \
                     --prefix PYTHONPATH ":" $program_PYTHONPATH \
                     --prefix PATH ":" $program_PATH
diff --git a/pkgs/top-level/python-packages.nix b/pkgs/top-level/python-packages.nix
index c0791d186ba9..5f79ddea816d 100644
--- a/pkgs/top-level/python-packages.nix
+++ b/pkgs/top-level/python-packages.nix
@@ -50,6 +50,32 @@ let
     { deps = pkgs.makeWrapper;
       substitutions.libPrefix = python.libPrefix;
       substitutions.executable = "${python}/bin/${python.executable}";
+      substitutions.magicalSedExpression = let
+        # Looks weird? Of course, it's between single quoted shell strings.
+        # NOTE: Order DOES matter here, so single character quotes need to be
+        #       at the last position.
+        quoteVariants = [ "'\"'''\"'" "\"\"\"" "\"" "'\"'\"'" ]; # hey Vim: ''
+
+        mkStringSkipper = labelNum: quote: let
+          label = "q${toString labelNum}";
+          isSingle = elem quote [ "\"" "'\"'\"'" ];
+          endQuote = if isSingle then "[^\\\\]${quote}" else quote;
+        in ''
+          /^ *[a-z]?${quote}/ {
+            /${quote}${quote}|${quote}.*${endQuote}/{n;br}
+            :${label}; n; /^${quote}/{n;br}; /${endQuote}/{n;br}; b${label}
+          }
+        '';
+
+      in ''
+        1 {
+          /^#!/!b; :r
+          /\\$/{N;br}
+          /__future__|^ *(#.*)?$/{n;br}
+          ${concatImapStrings mkStringSkipper quoteVariants}
+          /^ *[^# ]/i import sys; sys.argv[0] = '"'$(basename "$i")'"'
+        }
+      '';
     }
    ../development/python-modules/generic/wrap.sh;