Added python related nonsense to be ignored when summarizing stuff

.github/workflows/test-summarize.yml

@@ -16,7 +16,7 @@ jobs:
     strategy:
       matrix:
         os: [Ubuntu-latest, macOS-latest]
-        go-version: ['1.23.8', '1.24.2']
+        go-version: ['1.24.0']
       fail-fast: false  # Continue testing all combinations even if one fails
 
     steps:
@@ -47,13 +47,12 @@ jobs:
         run: |
           mkdir -p ${{ github.workspace }}/anotherProject
           echo -e "package main\n\nfunc main() {\n    println(\"Hello, World!\")\n}" > ${{ github.workspace }}/anotherProject/hello.go
-          mkdir -p ${{ github.workspace }}/summaries
         shell: bash
 
       - name: Test 1 Step 5 Run summarize with command-line arguments
         run: |
-          cd ${{ github.workspace }}/anotherProject
-          ${{ github.workspace }}/summarize -d . -o ${{ github.workspace }}/summaries
+          cd ${{ github.workspace }}
+          ${{ github.workspace }}/summarize -d anotherProject -o ${{ github.workspace }}/summaries
           ls -lh ${{ github.workspace }}/summaries/
         shell: bash
 
@@ -90,49 +89,3 @@ jobs:
           echo "Contents of $SUMMARY_FILE:"
           cat "$SUMMARY_FILE"
         shell: bash
-
-      # Step 9: Verify the summary contains the hello.go source code
-      - name: Test 1 Step 9 Verify summary contains hello.go source code (command-line usage)
-        run: |
-          SUMMARY_FILE="${{ steps.find-summary-cli.outputs.summary_file }}"
-          RANDOM_FILE="hello.go"
-          RANDOM_FILE_ABS="${{ github.workspace }}/anotherProject/hello.go"
-          echo "Checking if $SUMMARY_FILE contains the source code of $RANDOM_FILE"
-
-          SECTION_START=$(grep -n "^## $RANDOM_FILE$" "$SUMMARY_FILE" | cut -d: -f1)
-          if [ -z "$SECTION_START" ]; then
-            echo "Error: Could not find section for $RANDOM_FILE in $SUMMARY_FILE"
-            echo "Listing all section headers in $SUMMARY_FILE:"
-            grep "^## " "$SUMMARY_FILE"
-            exit 1
-          fi
-
-          CODE_START=$((SECTION_START + 3))
-          CODE_END=$(tail -n +$CODE_START "$SUMMARY_FILE" | grep -n "^\`\`\`$" | head -n 1 | cut -d: -f1 || true)
-          if [ -z "$CODE_END" ] || [ "$CODE_END" -eq 0 ]; then
-            echo "Error: Could not find code block end for $RANDOM_FILE in $SUMMARY_FILE"
-            echo "Dumping lines after section start for debugging (up to 20 lines):"
-            tail -n +$SECTION_START "$SUMMARY_FILE" | head -n 20
-            exit 1
-          fi
-          CODE_LINES=$((CODE_END - 1))
-          if [ $CODE_LINES -le 0 ]; then
-            echo "Error: Invalid code block length ($CODE_LINES lines) for $RANDOM_FILE"
-            echo "Dumping lines after section start for debugging (up to 20 lines):"
-            tail -n +$SECTION_START "$SUMMARY_FILE" | head -n 20
-            exit 1
-          fi
-          tail -n +$CODE_START "$SUMMARY_FILE" > temp_code_block.txt
-          head -n $CODE_LINES temp_code_block.txt > extracted_code.txt
-          rm temp_code_block.txt
-
-          cat "$RANDOM_FILE_ABS" > original_code.txt
-
-          diff -wB extracted_code.txt original_code.txt > diff_output.txt
-          if [ $? -ne 0 ]; then
-            echo "Error: The source code in the summary does not match the original file"
-            cat diff_output.txt
-            exit 1
-          fi
-          echo "Success: The source code of $RANDOM_FILE in $SUMMARY_FILE matches the original file"
-        shell: bash

.gitignore

@@ -2,4 +2,5 @@ summarize
 .idea
 .DS_Store
 *.log
-summaries/
+summaries/
+bin/

Makefile

@@ -0,0 +1,70 @@
+# Generic Makefile for Any Go Project (Lines 1-65)
+MAIN_PATH=.
+APP_NAME := $(shell basename "$(shell realpath $(MAIN_PATH))")
+BIN_DIR=bin
+
+# Go build flags
+# -s: Strip symbols (reduces binary size)
+# -w: Omit DWARF debugging information
+LDFLAGS=-ldflags "-s -w"
+
+.PHONY: all clean summary install darwin-amd64 darwin-amd64 linux-amd64 linux-arm64 windows-amd64
+
+# Create build directory if it doesn't exist
+$(BIN_DIR):
+	@mkdir -p $(BIN_DIR)
+
+# Build for all platforms
+all: darwin-amd64 darwin-arm64 linux-amd64 linux-arm64 windows-amd64 install
+
+summary:
+	@if ! command -v summarize > /dev/null; then \
+		go install github.com/andreimerlescu/summarize@latest; \
+	fi
+	@summarize -i "go,Makefile,mod" -debug -print
+
+install: $(BIN_DIR)
+	@if [[ "$(shell go env GOOS)" == "windows" ]]; then \
+		cp $(BIN_DIR)/$(APP_NAME)-$(shell go env GOOS)-$(shell go env GOARCH).exe "$(shell go env GOBIN)/$(APP_NAME).exe"; \
+	else \
+		cp $(BIN_DIR)/$(APP_NAME)-$(shell go env GOOS)-$(shell go env GOARCH) "$(shell go env GOBIN)/$(APP_NAME)"; \
+	fi
+	@echo "NEW: $(shell which $(APP_NAME))"
+
+# Build for macOS Intel (amd64)
+darwin-amd64: $(BIN_DIR)
+	@GOOS=darwin GOARCH=amd64 go build $(LDFLAGS) -o $(BIN_DIR)/$(APP_NAME)-darwin-amd64 $(MAIN_PATH)
+	@echo "NEW: $(BIN_DIR)/$(APP_NAME)-darwin-amd64"
+
+# Build for macOS Silicon (arm64)
+darwin-arm64: $(BIN_DIR)
+	@GOOS=darwin GOARCH=arm64 go build $(LDFLAGS) -o $(BIN_DIR)/$(APP_NAME)-darwin-arm64 $(MAIN_PATH)
+	@echo "NEW: $(BIN_DIR)/$(APP_NAME)-darwin-amd64"
+
+# Build for Linux ARM64
+linux-arm64: $(BIN_DIR)
+	@GOOS=linux GOARCH=arm64 go build $(LDFLAGS) -o $(BIN_DIR)/$(APP_NAME)-linux-arm64 $(MAIN_PATH)
+	@echo "NEW: $(BIN_DIR)/$(APP_NAME)-darwin-arm64"
+
+# Build for Linux AMD64
+linux-amd64: $(BIN_DIR)
+	@GOOS=linux GOARCH=amd64 go build $(LDFLAGS) -o $(BIN_DIR)/$(APP_NAME)-linux-amd64 $(MAIN_PATH)
+	@echo "NEW: $(BIN_DIR)/$(APP_NAME)-linux-amd64"
+
+# Build for Windows AMD64
+windows-amd64: $(BIN_DIR)
+	@GOOS=windows GOARCH=amd64 go build $(LDFLAGS) -o $(BIN_DIR)/$(APP_NAME).exe $(MAIN_PATH)
+	@echo "NEW: $(BIN_DIR)/$(APP_NAME).exe"
+
+# Clean build artifacts
+clean:
+	@rm -rf $(BIN_DIR)
+	@echo "REMOVED: $(BIN_DIR)"
+
+# Project Specific
+
+.PHONY: test
+
+# Run tests
+test:
+	./test.sh

README.md

@@ -1,16 +1,55 @@
 # Summarize 
 
-A go utility that will capture files with an extension pattern into a single markdown formatted
-file that looks like: 
+The **Summarize** package was designed for developers who wish to leverage the use of Artificial Intelligence while 
+working on a project. The `summarize` command give you a powerful interface that is managed by arguments and environment
+variables that define include/exclude extensions, and avoid substrings list while parsing paths. The binary has 
+concurrency built into it and has limits for the output file. It ignores its default output directory so it won't
+recursively build summaries upon itself. It defaults to writing to a new directory that it'll try to create in the
+current working directory called `summaries`, that I recommend that you add to your `.gitignore` and `.dockerignore`.
+
+I've found it useful to leverage the `make summary` command in all of my projects. This way, if I need to ask an AI a
+question about a piece of code, I can capture the source code of the entire directory quickly and then just `cat` the
+output file path provided and _voila_! The `-print` argument allows you to display the summary contents in the STDOUT
+instead of the `Summary generated: summaries/summary.2025.07.29.08.59.03.UTC.md` that it would normally generate.
+
+The **Environment** can be used to control the native behavior of the `summarize` binary, such that you won't be required
+to type the arguments out each time. If you use _JSON_ all the time, you can enable its output format on every command
+by using the `SUMMARIZE_ALWAYS_JSON`. If you always want to write the summary, you can use the `SUMMARIZE_ALWAYS_WRITE`
+variable. If you want to always print the summary to STDOUT instead of the success message, you can use the variable
+`SUMMARIZE_ALWAYS_PRINT`. If you want to compress the rendered summary every time, you can use the variable
+`SUMMARIZE_ALWAYS_COMPRESS`. These `SUMMARIZE_ALWAYS_*` environment variables are responsible for customizing the 
+runtime of the `summarize` application. 
+
+When the `summarize` binary runs, it'll do its best to ignore files that it can't render to a text file. This includes
+images, videos, binary files, and text files that are commonly linked to secrets.
+
+The developer experience while using `summarize` is designed to enable quick use with just running `summarize` from 
+where ever you wish to summarize. The `-d` for **source directory** defaults to `.` and the `-o`/`-f` for **output path**
+defaults to a new timestamped file (`-f`) in the (`-o`) `summaries/` directory from the `.` context. The `-i` and `-x` are used to
+define what to <b>i</b>nclude and e<b>x</b>clude various file extensions like `go,ts,py` etc.. The `-s` is used to 
+**skip** over substrings within a scanned path. Dotfiles can completely be ignored by all paths by using `-ndf` as a flag.
+
+Performance of the application can be tuned using the `-mf=<int>` to assign **Max Files** that will concurrently be
+processed. The default is 369. The `-max=<int64>` represents a limit on how large the rendered summary can become.
+
+Once the program finishes running, the rendered file will look similar to: 
 
 ```md
 # Project Summary
 
-### `filename.ext`
+<AI prompt description>
+
+### `filename.go`
+
+<File Info>
 
 <full source code>
 
-### `filename.ext`
+### `filename.cs`
+
+<File Info>
+
+<full source code>
 
 ... etc.
 
@@ -49,19 +88,139 @@ cd ~/work/anotherProject
 summarize -d anotherProject -o /home/user/summaries/anotherProject
 ```
 
-Since `figtree` is designed to be very functional, its lightweight but feature 
-intense design through simple biology memetics makes it well suited for this program. 
-
 ## Options
 
-| Name            | Argument | Type     | Usage                                                  |
-|-----------------|----------|----------|--------------------------------------------------------|
-| `kSourceDir`    | -d`      | `string` | Source directory path.                                 |
-| `kOutputDir`    | -o`      | `string` | Summary destination output directory path.             |
-| `kExcludeExt`   | `-x`     | `list`   | Comma separated string list of extensions to exclude.  |
-| `kSkipContains` | `-s`     | `list`   | Comma separated string to filename substrings to skip. |
-| `kIncludeExt`   | `-i`     | `list`   | Comma separated string of extensions to include.       |
-| `kFilename`     | `-f`     | `string` | Summary filename (writes to `-o` dir).                 | 
+| Name             | Argument | Type     | Usage                                                             |
+|------------------|----------|----------|-------------------------------------------------------------------|
+| `kSourceDir`     | `-d`     | `string` | Source directory path.                                            |
+| `kOutputDir`     | `-o`     | `string` | Summary destination output directory path.                        |
+| `kExcludeExt`    | `-x`     | `list`   | Comma separated string list of extensions to exclude.             |
+| `kSkipContains`  | `-s`     | `list`   | Comma separated string to filename substrings to skip.            |
+| `kIncludeExt`    | `-i`     | `list`   | Comma separated string of extensions to include.                  |
+| `kFilename`      | `-f`     | `string` | Summary filename (writes to `-o` dir).                            | 
+| `kVersion`       | `-v`     | `bool`   | When `true`, the binary version is shown                          |
+| `kCompress`      | `-gz`    | `bool`   | When `true`, **gzip** is used on the contents of the summary      |
+| `kMaxOutputSize` | `-max`   | `int64`  | Maximum size of the generated summary allowed                     |
+| `kPrint`         | `-print` | `bool`   | Uses STDOUT to write contents of summary                          |
+| `kWrite`         | `-write` | `bool`   | Uses the filesystem to save contents of summary                   |
+| `kDebug`         | `-debug` | `bool`   | When `true`, extra content is written to STDOUT aside from report | 
+
+
+## Environment
+
+| Environment Variable        | Type     | Default Value          | Usage                                                                                                       | 
+|-----------------------------|----------|------------------------|-------------------------------------------------------------------------------------------------------------|
+| `SUMMARIZE_CONFIG_FILE`     | `String` | `./config.yaml`        | Contents of the YAML Configuration to use for [figtree](https://github.com/andreimerlescu/figtree).         |
+| `SUMMARIZE_IGNORE_CONTAINS` | `List`   | \* see below           | Add items to this default list by creating your own new list here, they get concatenated.                   |
+| `SUMMARIZE_INCLUDE_EXT`     | `List`   | \*\* see below \*      | Add extensions to include in the summary in this environment variable, comma separated.                     |
+| `SUMMARIZE_EXCLUDE_EXT`     | `List`   | \*\*\* see below \* \* | Add exclusionary extensions to ignore to this environment variable, comma separated.                        |
+| `SUMMARIZE_ALWAYS_PRINT`    | `Bool`   | `false`                | When `true`, the `-print` will write the summary to STDOUT.                                                 |
+| `SUMMARIZE_ALWAYS_WRITE`    | `Bool`   | `false`                | When `true`, the `-write` will write to a new file on the disk.                                             | 
+| `SUMMARIZE_ALWAYS_JSON`     | `Bool`   | `false`                | When `true`, the `-json` flag will render JSON output to the console.                                       |
+| `SUMMARIZE_ALWAYS_COMPRESS` | `Bool`   | `false`                | When `true`, the `-gz` flag will use gzip to compress the summary contents and appends `.gz` to the output. |
+
+
+### \* Default `SUMMARIZE_IGNORE_CONTAINS` Value
+
+```json
+7z,gz,xz,zst,zstd,bz,bz2,bzip2,zip,tar,rar,lz4,lzma,cab,arj,crt,cert,cer,key,pub,asc,pem,p12,pfx,jks,keystore,id_rsa,id_dsa,id_ed25519,id_ecdsa,gpg,pgp,exe,dll,so,dylib,bin,out,o,obj,a,lib,dSYM,class,pyc,pyo,__pycache__,jar,war,ear,apk,ipa,dex,odex,wasm,node,beam,elc,iso,img,dmg,vhd,vdi,vmdk,qcow2,db,sqlite,sqlite3,db3,mdb,accdb,sdf,ldb,log,trace,dump,crash,jpg,jpeg,png,gif,bmp,tiff,tif,webp,ico,svg,heic,heif,raw,cr2,nef,dng,mp3,wav,flac,aac,ogg,wma,m4a,opus,aiff,mp4,avi,mov,mkv,webm,flv,wmv,m4v,3gp,ogv,ttf,otf,woff,woff2,eot,fon,pfb,pfm,pdf,doc,docx,xls,xlsx,ppt,pptx,odt,ods,odp,rtf,suo,sln,user,ncb,pdb,ipch,ilk,tlog,idb,aps,res,iml,idea,vscode,project,classpath,factorypath,prefs,vcxproj,vcproj,filters,xcworkspace,xcuserstate,xcscheme,pbxproj,DS_Store,Thumbs.db,desktop.ini,lock,sum,resolved,tmp,temp,swp,swo,bak,backup,orig,rej,patch,~,old,new,part,incomplete,map,min.js,min.css,bundle.js,bundle.css,chunk.js,dat,data,cache,pid,sock,pack,idx,rev,pickle,pkl,npy,npz,mat,rdata,rds
+```
+
+```go
+
+// defaultExclude are the -exc list of extensions that will be skipped automatically
+defaultExclude = []string{
+    // Compressed archives
+    "7z", "gz", "xz", "zst", "zstd", "bz", "bz2", "bzip2", "zip", "tar", "rar", "lz4", "lzma", "cab", "arj",
+
+    // Encryption, certificates, and sensitive keys
+    "crt", "cert", "cer", "key", "pub", "asc", "pem", "p12", "pfx", "jks", "keystore",
+    "id_rsa", "id_dsa", "id_ed25519", "id_ecdsa", "gpg", "pgp",
+
+    // Binary & executable artifacts
+    "exe", "dll", "so", "dylib", "bin", "out", "o", "obj", "a", "lib", "dSYM",
+    "class", "pyc", "pyo", "__pycache__",
+    "jar", "war", "ear", "apk", "ipa", "dex", "odex",
+    "wasm", "node", "beam", "elc",
+
+    // System and disk images
+    "iso", "img", "dmg", "vhd", "vdi", "vmdk", "qcow2",
+
+    // Database files
+    "db", "sqlite", "sqlite3", "db3", "mdb", "accdb", "sdf", "ldb",
+
+    // Log files
+    "log", "trace", "dump", "crash",
+
+    // Media files - Images
+    "jpg", "jpeg", "png", "gif", "bmp", "tiff", "tif", "webp", "ico", "svg", "heic", "heif", "raw", "cr2", "nef", "dng",
+
+    // Media files - Audio
+    "mp3", "wav", "flac", "aac", "ogg", "wma", "m4a", "opus", "aiff",
+
+    // Media files - Video
+    "mp4", "avi", "mov", "mkv", "webm", "flv", "wmv", "m4v", "3gp", "ogv",
+
+    // Font files
+    "ttf", "otf", "woff", "woff2", "eot", "fon", "pfb", "pfm",
+
+    // Document formats (typically not source code)
+    "pdf", "doc", "docx", "xls", "xlsx", "ppt", "pptx", "odt", "ods", "odp", "rtf",
+
+    // IDE/Editor/Tooling artifacts
+    "suo", "sln", "user", "ncb", "pdb", "ipch", "ilk", "tlog", "idb", "aps", "res",
+    "iml", "idea", "vscode", "project", "classpath", "factorypath", "prefs",
+    "vcxproj", "vcproj", "filters", "xcworkspace", "xcuserstate", "xcscheme", "pbxproj",
+    "DS_Store", "Thumbs.db", "desktop.ini",
+
+    // Package manager and build artifacts
+    "lock", "sum", "resolved", // package-lock.json, go.sum, yarn.lock, etc.
+
+    // Temporary and backup files
+    "tmp", "temp", "swp", "swo", "bak", "backup", "orig", "rej", "patch",
+    "~", "old", "new", "part", "incomplete",
+
+    // Source maps and minified files (usually generated)
+    "map", "min.js", "min.css", "bundle.js", "bundle.css", "chunk.js",
+
+    // Configuration that's typically binary or generated
+    "dat", "data", "cache", "pid", "sock",
+
+    // Version control artifacts (though usually in ignored directories)
+    "pack", "idx", "rev",
+
+    // Other binary formats
+    "pickle", "pkl", "npy", "npz", "mat", "rdata", "rds",
+}
+
+```
+
+### \* \* Default `SUMMARIZE_INCLUDE_EXT`
+
+```json
+go,ts,tf,sh,py,js,Makefile,mod,Dockerfile,dockerignore,gitignore,esconfigs,md
+```
+
+```go
+// defaultInclude are the -inc list of extensions that will be included in the summary
+defaultInclude = []string{
+    "go", "ts", "tf", "sh", "py", "js", "Makefile", "mod", "Dockerfile", "dockerignore", "gitignore", "esconfigs", "md",
+}
+```
+
+### \* \* \* Default `SUMMARIZE_EXCLUDE_EXT`
+
+```json
+.min.js,.min.css,.git/,.svn/,.vscode/,.vs/,.idea/,logs/,secrets/,.venv/,/site-packages,.terraform/,summaries/,node_modules/,/tmp,tmp/,logs/
+```
+
+```go
+// defaultAvoid are the -avoid list of substrings in file path names to avoid in the summary
+defaultAvoid = []string{
+    ".min.js", ".min.css", ".git/", ".svn/", ".vscode/", ".vs/", ".idea/", "logs/", "secrets/",
+    ".venv/", "/site-packages", ".terraform/", "summaries/", "node_modules/", "/tmp", "tmp/", "logs/",
+}
+```
 
 ## Contribution 
 

VERSION

@@ -1 +1 @@
-v1.0.0
+v1.0.2

go.mod

@@ -1,16 +1,17 @@
 module github.com/andreimerlescu/summarize
 
-go 1.23.7
+go 1.24.5
 
 require (
-	github.com/andreimerlescu/checkfs v1.0.2
-	github.com/andreimerlescu/figtree/v2 v2.0.3
+	github.com/andreimerlescu/checkfs v1.0.4
+	github.com/andreimerlescu/figtree/v2 v2.0.14
 	github.com/andreimerlescu/sema v1.0.0
 )
 
 require (
+	github.com/andreimerlescu/bump v1.0.3 // indirect
 	github.com/go-ini/ini v1.67.0 // indirect
-	golang.org/x/sys v0.31.0 // indirect
-	golang.org/x/term v0.30.0 // indirect
+	golang.org/x/sys v0.33.0 // indirect
+	golang.org/x/term v0.32.0 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
 )