spike to check latex for basic errors before compile

Aims to solve following problems which are currently not visible to user:

- project is too big, which files are worst offenders?
- when there are duplicate file names so an 'old' version keeps overrighting a new version
- when a file has the same path as a folder which blows up clsi i.e. images/research images/research/1.png

services/web/app/coffee/Features/Compile/ClsiManager.coffee

@@ -7,6 +7,8 @@ ProjectEntityHandler = require("../Project/ProjectEntityHandler")
 logger = require "logger-sharelatex"
 url = require("url")
 ClsiCookieManager = require("./ClsiCookieManager")
+_ = require("underscore")
+async = require("async")
 
 
 module.exports = ClsiManager =
@@ -153,3 +155,70 @@ module.exports = ClsiManager =
 					logger.error err: error, project_id: project_id, "CLSI returned failure code"
 					callback error, body
 
+	_checkRecoursesForErrors: (resources, callback)->
+		jobs = 
+			duplicatePaths: (cb)->
+				ClsiManager._checkForFilesWithSameName resources, cb
+
+			conflictedPaths: (cb)->
+				ClsiManager._checkForConflictingPaths resources, cb
+
+			sizeCheck: (cb)->
+				ClsiManager._checkDocsAreUnderSizeLimit resources, cb
+				
+		async.series jobs, callback
+
+	_checkForFilesWithSameName: (resources, callback)->
+		paths = _.pluck(resources, 'path')
+
+		duplicates = _.filter paths, (path)->
+			return _.countBy(paths)[path] > 1
+
+		duplicates = _.uniq(duplicates)
+
+		duplicateObjects = _.map duplicates, (dup)->
+			path:dup
+
+		callback(null, duplicateObjects)
+
+	_checkForConflictingPaths: (resources, callback)->
+		paths = _.pluck(resources, 'path')
+
+		conflicts = _.filter paths, (path)->
+			matchingPaths = _.filter paths, (checkPath)->
+				return checkPath.indexOf(path+"/") != -1
+
+			return matchingPaths.length > 0
+
+		conflictObjects = _.map conflicts, (conflict)->
+			path:conflict
+
+		callback null, conflictObjects
+
+	_checkDocsAreUnderSizeLimit: (resources, callback)->
+		
+		FIVEMB = 1000 * 1000 * 5
+
+		totalSize = 0
+
+		sizedResources = _.map resources, (resource)->
+			result = {path:resource.path}
+			if resource.content?
+				result.size = resource.content.join("").length
+			else
+				result.size = 0
+			totalSize += result.size
+			return result
+
+		tooLarge = totalSize > FIVEMB
+
+		sizedResources = _.sortBy(sizedResources, "size").slice(10).reverse()
+
+		callback(null, {resources:sizedResources, totalSize:totalSize, tooLarge:tooLarge})
+
+
+
+
+
+
+

services/web/test/UnitTests/coffee/Compile/ClsiManagerTests.coffee

@@ -320,15 +320,89 @@ describe "ClsiManager", ->
 
 
 
-
+	describe "_checkRecoursesForErrors", ->
-
+
-
+		beforeEach ->
-
+			@resources = [{
-
+				path:    "main.tex"
-
+				content: ["stuff"]
-
+			}, {
-
+				path:    "chapters/chapter1"
-
+				content: ["other stuff"]
+			}, {
+				path: "stuff/image/image.png"
+				url:  "#{@settings.apis.filestore.url}/project/#{@project_id}/file/1234124321312"
+				modified: ["more stuff"]
+			}]
+
+		it "should call _checkForFilesWithSameName and _checkForConflictingPaths", (done)->
+
+			@ClsiManager._checkForFilesWithSameName = sinon.stub().callsArgWith(1)
+			@ClsiManager._checkForConflictingPaths = sinon.stub().callsArgWith(1)
+			@ClsiManager._checkDocsAreUnderSizeLimit = sinon.stub().callsArgWith(1)
+			@ClsiManager._checkRecoursesForErrors @resources, =>
+				@ClsiManager._checkForFilesWithSameName.called.should.equal true
+				@ClsiManager._checkForConflictingPaths.called.should.equal true
+				@ClsiManager._checkDocsAreUnderSizeLimit.called.should.equal true
+				done()
+
+		describe "_checkForFilesWithSameName", ->
+
+			it "should flag up 2 nested files with same path", (done)->
+
+				@resources.push({
+					path: "chapters/chapter1"
+					url: "http://somwhere.com"
+				})
+
+				@ClsiManager._checkForFilesWithSameName @resources, (err, duplicateErrors)->
+					duplicateErrors.length.should.equal 1
+					duplicateErrors[0].path.should.equal "chapters/chapter1"
+					done()
+
+		describe "_checkForConflictingPaths", ->
+
+			it "should flag up when a nested file has folder with same subpath as file elsewhere", (done)->
+				@resources.push({
+					path: "stuff/image"
+					url: "http://somwhere.com"
+				})
+
+				@resources.push({
+					path:    "chapters/chapter1.tex"
+					content: ["other stuff"]
+				})
+
+				@resources.push({
+					path:    "chapters.tex"
+					content: ["other stuff"]
+				})
+
+				@ClsiManager._checkForConflictingPaths @resources, (err, conflictPathErrors)->
+					conflictPathErrors.length.should.equal 1
+					conflictPathErrors[0].path.should.equal "stuff/image"
+					done()
+				
+
+		describe "_checkDocsAreUnderSizeLimit", ->
+
+			it "should error when there is more than 2mb of data", (done)->
+
+				@resources.push({
+					path:    "massive.tex"
+					content: [require("crypto").randomBytes(1000 * 1000 * 5).toString("hex")]
+				})
+
+				while @resources.length < 20
+					@resources.push({path:"chapters/chapter1.tex",url: "http://somwhere.com"})
+
+				@ClsiManager._checkDocsAreUnderSizeLimit @resources, (err, sizeError)->
+					sizeError.tooLarge.should.equal true
+					sizeError.totalSize.should.equal 10000016
+					sizeError.resources.length.should.equal 10
+					sizeError.resources[0].path.should.equal "massive.tex"
+					sizeError.resources[0].size.should.equal 1000 * 1000 * 10
+					done()